Ordinal Optimization and Multi Armed Bandit Techniques
|
|
- Kerry Reynolds
- 5 years ago
- Views:
Transcription
1 Ordinal Optimization and Multi Armed Bandit Techniques Sandeep Juneja. with Peter Glynn September 10, 2014
2 The ordinal optimization problem Determining the best of d alternative designs for a system, on the basis of Monte Carlo simulation of each of the designs.
3 The ordinal optimization problem Determining the best of d alternative designs for a system, on the basis of Monte Carlo simulation of each of the designs. More precisely, the d different designs are compared on the basis of an associated (random) performance measure X (i), i d, and the goal is to identify i = arg min 1 j d µ(j), where µ(j) EX (j), 1 j d. Goal is only to identify the best design and not to actually estimate the performance.
4 The ordinal optimization problem Determining the best of d alternative designs for a system, on the basis of Monte Carlo simulation of each of the designs. More precisely, the d different designs are compared on the basis of an associated (random) performance measure X (i), i d, and the goal is to identify i = arg min 1 j d µ(j), where µ(j) EX (j), 1 j d. Goal is only to identify the best design and not to actually estimate the performance. We have the ability to generate iid realizations of each of the d random variables.
5 The ordinal optimization problem Determining the best of d alternative designs for a system, on the basis of Monte Carlo simulation of each of the designs. More precisely, the d different designs are compared on the basis of an associated (random) performance measure X (i), i d, and the goal is to identify i = arg min 1 j d µ(j), where µ(j) EX (j), 1 j d. Goal is only to identify the best design and not to actually estimate the performance. We have the ability to generate iid realizations of each of the d random variables. We focus primarily on d = 2, so given independent samples of X we want to find if the mean is positive or negative.
6 Talk Overview Estimating difference of mean values relies on central limit theorem with an associated slow convergence rate.
7 Talk Overview Estimating difference of mean values relies on central limit theorem with an associated slow convergence rate. Ho and others observed (1990) that identifying the best system typically has a faster convergence rate.
8 Talk Overview Estimating difference of mean values relies on central limit theorem with an associated slow convergence rate. Ho and others observed (1990) that identifying the best system typically has a faster convergence rate. Dai (1996) showed in a fairly general framework using large deviation methods that the probability of false selection decays at an exponential rate under mild light tailed assumptions.
9 Talk Overview Glynn and J (2004) optimized the large deviations function associated with this probability to determine optimal computational budget allocation to each design to minimise the false selection probability. Significant literature since then relying on large deviations analysis.
10 Talk Overview Glynn and J (2004) optimized the large deviations function associated with this probability to determine optimal computational budget allocation to each design to minimise the false selection probability. Significant literature since then relying on large deviations analysis. Expectation was that one can get algorithms that can guarantee that the probability of error is upper bounded by δ using O(log(1/δ)) computational effort.
11 Talk Overview Glynn and J (2004) optimized the large deviations function associated with this probability to determine optimal computational budget allocation to each design to minimise the false selection probability. Significant literature since then relying on large deviations analysis. Expectation was that one can get algorithms that can guarantee that the probability of error is upper bounded by δ using O(log(1/δ)) computational effort. However these large deviations-based methods need to estimate the underlying large deviations rate functions from the samples generated.
12 We argue through two reasonable settings that these rate functions are difficult to estimate accurately (NOT due to the heavy tails of estimated MGFs), the probability of mis-estimation will generally dominate the underlying large deviations probability, making it difficult to build algorithms with log(1/δ) convergence rate.
13 We argue through two reasonable settings that these rate functions are difficult to estimate accurately (NOT due to the heavy tails of estimated MGFs), the probability of mis-estimation will generally dominate the underlying large deviations probability, making it difficult to build algorithms with log(1/δ) convergence rate. Further we show that given any (ɛ, δ) algorithm - one that correctly separates designs with mean difference at least ɛ with probability at least 1 δ, given any constant K one can always find designs (in a large class) that require larger than K log(1/δ) effort.
14 We argue through two reasonable settings that these rate functions are difficult to estimate accurately (NOT due to the heavy tails of estimated MGFs), the probability of mis-estimation will generally dominate the underlying large deviations probability, making it difficult to build algorithms with log(1/δ) convergence rate. Further we show that given any (ɛ, δ) algorithm - one that correctly separates designs with mean difference at least ɛ with probability at least 1 δ, given any constant K one can always find designs (in a large class) that require larger than K log(1/δ) effort. Under explicitly available moment upper bounds, we develop truncation based O(log(1/δ)) computation time (ɛ, δ) algorithms.
15 We also adapt the recently proposed sequential algorithms in multi-armed bandit regret setting to this pure exploration setting. We argue through two reasonable settings that these rate functions are difficult to estimate accurately (NOT due to the heavy tails of estimated MGFs), the probability of mis-estimation will generally dominate the underlying large deviations probability, making it difficult to build algorithms with log(1/δ) convergence rate. Further we show that given any (ɛ, δ) algorithm - one that correctly separates designs with mean difference at least ɛ with probability at least 1 δ, given any constant K one can always find designs (in a large class) that require larger than K log(1/δ) effort. Under explicitly available moment upper bounds, we develop truncation based O(log(1/δ)) computation time (ɛ, δ) algorithms.
16 A two phase implementation Consider a single rv X with unknown mean EX. Need to decide whether EX > 0 or EX 0 with error probability δ (as δ 0).
17 A two phase implementation Consider a single rv X with unknown mean EX. Need to decide whether EX > 0 or EX 0 with error probability δ (as δ 0). If we knew the large deviations rate function I (x) = sup θ R (θx Λ(θ)) (here Λ(θ) = log Ee θx )
18 A two phase implementation Consider a single rv X with unknown mean EX. Need to decide whether EX > 0 or EX 0 with error probability δ (as δ 0). If we knew the large deviations rate function I (x) = sup θ R (θx Λ(θ)) (here Λ(θ) = log Ee θx ) Then if EX < 0, we may take exp( n inf x 0 I (x)) as a proxy for the probability of false selection.
19 A two phase implementation Consider a single rv X with unknown mean EX. Need to decide whether EX > 0 or EX 0 with error probability δ (as δ 0). If we knew the large deviations rate function I (x) = sup θ R (θx Λ(θ)) (here Λ(θ) = log Ee θx ) Then if EX < 0, we may take exp( n inf x 0 I (x)) as a proxy for the probability of false selection. Recall that I(x) EX x
20 A two phase implementation... Hence, proxy exp( ni (0)) for false probability
21 A two phase implementation... Hence, proxy exp( ni (0)) for false probability This proxy holds even if EX > 0.
22 A two phase implementation... Hence, proxy exp( ni (0)) for false probability This proxy holds even if EX > 0. Thus, log(1/δ) I (0) samples ensure that P(FS) δ.
23 Hence, one reasonable estimation procedure is
24 Hence, one reasonable estimation procedure is Generate m = log(1/δ) samples in the first phase to estimate I (0) by Î m (0).
25 Hence, one reasonable estimation procedure is Generate m = log(1/δ) samples in the first phase to estimate I (0) by Î m (0). Generate log(1/δ)/îm (0) = m/î m (0) samples of X in the second phase and decide the sign of EX based on whether the sample average X m > 0 or X m 0.
26 Hence, one reasonable estimation procedure is Generate m = log(1/δ) samples in the first phase to estimate I (0) by Î m (0). Generate log(1/δ)/îm (0) = m/î m (0) samples of X in the second phase and decide the sign of EX based on whether the sample average X m > 0 or X m 0. We now discuss some pitfalls of this methodology.
27 Graphic view of I(0) The log-moment generating function of X Λ(θ) = log E exp(θx ) is convex with Λ(0) = 0 and Λ (0) = EX.
28 Graphic view of I(0) The log-moment generating function of X Λ(θ) = log E exp(θx ) is convex with Λ(0) = 0 and Λ (0) = EX. Then, I (0) = inf θ Λ(θ).
29 Λ(θ) Graphic view of I(0) The log-moment generating function of X Λ(θ) = log E exp(θx ) is convex with Λ(0) = 0 and Λ (0) = EX. Then, I (0) = inf θ Λ(θ). EX I(0) θ
30 Estimating I (0) We generate samples X 1,..., X m and first estimate the function ( ) 1 m ˆΛ m (θ) = log exp(θx i ). m and set Î m (0) = inf θ ˆΛ m (θ). i=1
31 Estimating I (0) We generate samples X 1,..., X m and first estimate the function ( ) 1 m ˆΛ m (θ) = log exp(θx i ). m and set Î m (0) = inf θ ˆΛ m (θ). Then we generate log(1/δ)/î m (0) = m/î m (0) samples of X in the second phase. i=1
32 Estimating I (0) We generate samples X 1,..., X m and first estimate the function ( ) 1 m ˆΛ m (θ) = log exp(θx i ). m and set Î m (0) = inf θ ˆΛ m (θ). Then we generate log(1/δ)/î m (0) = m/î m (0) samples of X in the second phase. Note that large values of exp(θx i ) raise the curve, do not lower it. i=1
33 Estimating I (0) We generate samples X 1,..., X m and first estimate the function ( ) 1 m ˆΛ m (θ) = log exp(θx i ). m and set Î m (0) = inf θ ˆΛ m (θ). Then we generate log(1/δ)/î m (0) = m/î m (0) samples of X in the second phase. Note that large values of exp(θx i ) raise the curve, do not lower it. i=1 The undersampling in the second phase happens due to conspiratorial large deviations behaviour of all the terms.
34 Λ(θ) Graphic view of estimated log moment generating function θ Im(0)
35 Lower Bounding P(FS) For expository convenience, take P(FS) E exp( m Î m (0) I (0)) where m = log(1/δ).
36 Lower Bounding P(FS) For expository convenience, take where m = log(1/δ). Then, for a > 0. P(FS) E exp( m Î m (0) I (0)) 1 1 m log P(FS) sup log E exp( m θ m ˆΛ m (θ) I (0)) 1 sup log exp( m θ m a ɛ I (0)) P(ˆΛ m (θ) ( a ɛ, a ɛ)),
37 Then lim inf m 1 m ( log P(FS) sup sup I (0) ) a>0 θ a I θ(e a ) where I θ (ν) = sup(αν log E exp(αe θx )). α
38 Then lim inf m 1 m ( log P(FS) sup sup I (0) ) a>0 θ a I θ(e a ) where I θ (ν) = sup(αν log E exp(αe θx )). α Further, I θ (e I (0) ) = 0 for θ so that inf θ Λ(θ) = Λ(θ ). lim inf m 1 log P(FS) 1. m
39 Another common estimation method Generate m = c log(1/δ) samples in the first phase to estimate I (0) by Î m (0).
40 Another common estimation method Generate m = c log(1/δ) samples in the first phase to estimate I (0) by Î m (0). If exp( mîm(0)) δ, stop.
41 Another common estimation method Generate m = c log(1/δ) samples in the first phase to estimate I (0) by Î m (0). If exp( mîm(0)) δ, stop. Else, provide another c log(1/δ) of computational budget and so on.
42 Another common estimation method Generate m = c log(1/δ) samples in the first phase to estimate I (0) by Î m (0). If exp( mîm(0)) δ, stop. Else, provide another c log(1/δ) of computational budget and so on. We now identify distributions for which this would not be accurate.
43 Need to find X with EX < 0 so that X m 0 and exp( mî m (0)) δ with probability higher than δ. (Recall m = c log(1/δ)).
44 Need to find X with EX < 0 so that X m 0 and exp( mî m (0)) δ with probability higher than δ. (Recall m = c log(1/δ)). Choose X so that exp( c log(1/δ)i (0)) >> δ so that or 0 > inf θ I (0) < 1/c Λ(θ) > 1/c.
45 title Furthermore, P( X m 0 and exp( mî m (0)) δ) δ
46 title Furthermore, P( X m 0 and exp( mî m (0)) δ) δ Suffices to find θ < 0 such that P(ˆΛ(θ) 1/c) δ
47 title Furthermore, P( X m 0 and exp( mî m (0)) δ) δ Suffices to find θ < 0 such that P(ˆΛ(θ) 1/c) δ Roughly then, Or exp( mi θ (e 1/c )) > δ. I θ (e 1/c ) < 1/c.
48 title Furthermore, P( X m 0 and exp( mî m (0)) δ) δ Suffices to find θ < 0 such that P(ˆΛ(θ) 1/c) δ Roughly then, Or exp( mi θ (e 1/c )) > δ. I θ (e 1/c ) < 1/c. Theorem - Stay Tuned
49 Λ(θ) Graphic view -1/c θ
50 Stronger negative result (adapted from Lai and Robbins 1985, Manor and Tsitsiklis 2004) Let D contain pdfs such that If f, g D then I (g, f ) ( ) log g(x) f (x) g(x)dx <.
51 Stronger negative result (adapted from Lai and Robbins 1985, Manor and Tsitsiklis 2004) Let D contain pdfs such that If f, g D then I (g, f ) ( ) log g(x) f (x) g(x)dx <. Each g D has a finite moment generating function in the neighbourhood of zero.
52 Stronger negative result (adapted from Lai and Robbins 1985, Manor and Tsitsiklis 2004) Let D contain pdfs such that If f, g D then I (g, f ) ( ) log g(x) f (x) g(x)dx <. Each g D has a finite moment generating function in the neighbourhood of zero. Suppose there exists an (ɛ, δ) policy, i.e., given two arms separated by a mean of at least ɛ 0, it finds the arm with the largest mean with probability at least 1 δ. Let T g (ɛ, δ) be the time it spends on arm g.
53 Stronger negative result (adapted from Lai and Robbins 1985, Manor and Tsitsiklis 2004) Let D contain pdfs such that If f, g D then I (g, f ) ( ) log g(x) f (x) g(x)dx <. Each g D has a finite moment generating function in the neighbourhood of zero. Suppose there exists an (ɛ, δ) policy, i.e., given two arms separated by a mean of at least ɛ 0, it finds the arm with the largest mean with probability at least 1 δ. Let T g (ɛ, δ) be the time it spends on arm g. Then, lim inf δ 0 ET g (ɛ, δ) log(1/δ) for g, f D, µ g < µ f ɛ. Const. I (g, f ) + O(ɛ)
54 Same output different measures Let such that Λ f (θ ɛ) = µ f + ɛ f θɛ (x) = exp(θ ɛ x Λ f (θ ɛ ))f (x) P A g f Y 1 Y 2 X 1 X 2 Y T2 P B f f X T1
55 Note that P A ( algorithm announces f ) 1 δ
56 Note that P A ( algorithm announces f ) 1 δ P B (f ) δ
57 Note that P A ( algorithm announces f ) 1 δ P B (f ) δ T g P B (f ) = E PA ( i=1 f θɛ (Y i ) I (f )) g(y i ) = E PA (e Tg g(y i ) Tg i=1 f (Y i ) +θɛ i=1 Y i T g Λ f (θ ɛ) I (f )) = E PA (e ETg I (g,f )+ETg (θɛµg Λ f (θ ɛ))+small I (set high prob)). And the result is easily deduced.
58 Way forward Additional information needed to attain log(1/δ) convergence rates.
59 Way forward Additional information needed to attain log(1/δ) convergence rates. Great deal of structure is typically known about models used in simulation. Often upper bounds on moments may be available
60 Way forward Additional information needed to attain log(1/δ) convergence rates. Great deal of structure is typically known about models used in simulation. Often upper bounds on moments may be available Easy to develop such bounds once suitable Lyapunov functions can be identified (not to be discussed here)
61 Way forward Additional information needed to attain log(1/δ) convergence rates. Great deal of structure is typically known about models used in simulation. Often upper bounds on moments may be available Easy to develop such bounds once suitable Lyapunov functions can be identified (not to be discussed here) Assuming that such bounds are available, one may use them to develop (ɛ, δ) strategies by truncating random variables while controlling the error to be less than ɛ. Using Hoeffding type bounds for bounded random variables.
62 Way forward Additional information needed to attain log(1/δ) convergence rates. Great deal of structure is typically known about models used in simulation. Often upper bounds on moments may be available Easy to develop such bounds once suitable Lyapunov functions can be identified (not to be discussed here) Assuming that such bounds are available, one may use them to develop (ɛ, δ) strategies by truncating random variables while controlling the error to be less than ɛ. Using Hoeffding type bounds for bounded random variables. Multi-armed-bandits methods have been recently developed that do this in a sequential and adaptive manner.
63 A useful observation Suppose X is a class of non-negative random variables and f is a strictly increasing convex function.
64 A useful observation Suppose X is a class of non-negative random variables and f is a strictly increasing convex function. Consider the optimization problem max X X EXI (X x) such that Ef (X ) a,
65 A useful observation Suppose X is a class of non-negative random variables and f is a strictly increasing convex function. Consider the optimization problem max X X EXI (X x) such that Ef (X ) a, This has a two point solution relying on observation that if Y = E[X X < x]i (X < x) + E[X X x]i (X x) then EY = EX, EYI (Y x) = EXI (X x) and Ef (Y ) Ef (X ).
66 Obtaining exponential convergence guarantees We consider X ɛ = {X : EX > ɛ} where each X = A B and A, B are non-negative.
67 Obtaining exponential convergence guarantees We consider X ɛ = {X : EX > ɛ} where each X = A B and A, B are non-negative. We assume that we can find R a ( ɛ), R b ( ɛ) that truncate the excess mean by at least ɛ for each such value.
68 Obtaining exponential convergence guarantees We consider X ɛ = {X : EX > ɛ} where each X = A B and A, B are non-negative. We assume that we can find R a ( ɛ), R b ( ɛ) that truncate the excess mean by at least ɛ for each such value. If X = A B X ɛ, then AI (A < R a (βɛ)) BI (B < R b (βɛ)) X (1 β)ɛ.
69 Our algorithm then is:
70 Our algorithm then is: 1. Generate n independent samples of AI (A < R a (βɛ)) BI (B < R b (βɛ)).
71 Our algorithm then is: 1. Generate n independent samples of AI (A < R a (βɛ)) BI (B < R b (βɛ)). 2. Refer to these as Y 1, Y 2,..., Y n and compute Ȳ n = 1 n n Y i. i=1
72 Our algorithm then is: 1. Generate n independent samples of AI (A < R a (βɛ)) BI (B < R b (βɛ)). 2. Refer to these as Y 1, Y 2,..., Y n and compute Ȳ n = 1 n n Y i. i=1 3. If Ȳ n 0, declare that EX > 0.
73 Our algorithm then is: 1. Generate n independent samples of AI (A < R a (βɛ)) BI (B < R b (βɛ)). 2. Refer to these as Y 1, Y 2,..., Y n and compute Ȳ n = 1 n n Y i. i=1 3. If Ȳ n 0, declare that EX > If Ȳn < 0, declare that EX < 0.
74 titleusing Hoeffding Inequality to bound P(FS) Suppose that EX < ɛ. Then, EY i < (1 β)ɛ. Also, R b (βɛ) Y i R a (βɛ).
75 titleusing Hoeffding Inequality to bound P(FS) Suppose that EX < ɛ. Then, EY i < (1 β)ɛ. Also, R b (βɛ) Y i R a (βɛ). One can select n δ = (R a(βɛ) + R b (βɛ)) 2 2(1 β) 2 ɛ 2 log(1/δ).
76 titleusing Hoeffding Inequality to bound P(FS) Suppose that EX < ɛ. Then, EY i < (1 β)ɛ. Also, R b (βɛ) Y i R a (βɛ). One can select n δ = (R a(βɛ) + R b (βɛ)) 2 2(1 β) 2 ɛ 2 log(1/δ). Furthermore, β may be selected to minimize (R a (βɛ) + R b (βɛ)) 2 (1 β) 2.
77 Pure exploration bandit algorithms Total n arms. Each arm a when sampled gives a Bernoulli reward with mean µ a > 0.
78 Pure exploration bandit algorithms Total n arms. Each arm a when sampled gives a Bernoulli reward with mean µ a > 0. Let arm with the largest mean a = arg max a A µ a and let a = µ a µ a be assumed be positive for all a a.
79 Pure exploration bandit algorithms Total n arms. Each arm a when sampled gives a Bernoulli reward with mean µ a > 0. Let arm with the largest mean a = arg max a A µ a and let a = µ a µ a be assumed be positive for all a a. Even Dar, Mannor and Mansour 2006 devise a sequential sampling strategy amongst these arms to find a with probability at least 1 δ, (for a pre-specified small δ) with total number of samples generated of O ln(n/δ) 2. a a a
80 Foundational observation in much of the related Bandit literature Suppose that for an arm a with mean µ a, the sample mean based on t observations is denoted by ˆµ t a.
81 Foundational observation in much of the related Bandit literature Suppose that for an arm a with mean µ a, the sample mean based on t observations is denoted by ˆµ t a. Let α t = log(5nt 2 /δ)/t.
82 Foundational observation in much of the related Bandit literature Suppose that for an arm a with mean µ a, the sample mean based on t observations is denoted by ˆµ t a. Let α t = log(5nt 2 /δ)/t. Let E a,δ = { ˆµ t a µ a < α t for all t.}
83 Foundational observation in much of the related Bandit literature Suppose that for an arm a with mean µ a, the sample mean based on t observations is denoted by ˆµ t a. Let α t = log(5nt 2 /δ)/t. Let E a,δ = { ˆµ t a µ a < α t for all t.} Then, from Hoeffding, we have for any t, P( ˆµ t a µ a α t ) 2δ 5nt 2.
84 Hence, it follows that P(E a,δ ) 1 δ/n, so that if E δ = a E a,δ, then P(E δ ) 1 δ.
85 Hence, it follows that P(E a,δ ) 1 δ/n, so that if E δ = a E a,δ, then P(E δ ) 1 δ. Their algorithm relies on the fact that on E δ it always picks the correct winner and on this set quickly fathoms away the losers.
86 Successive Rejection Algorithm Sample every arm a once and let ˆµ t a be the average reward of arm a by time t;
87 Successive Rejection Algorithm Sample every arm a once and let ˆµ t a be the average reward of arm a by time t; Let ˆµ t max = max a ˆµ t a and recall that α t = log(5nt 2 /δ)/t;
88 Successive Rejection Algorithm Sample every arm a once and let ˆµ t a be the average reward of arm a by time t; Let ˆµ t max = max a ˆµ t a and recall that α t = log(5nt 2 /δ)/t; Each arm a such that ˆµ t max ˆµ t a 2α t is removed from consideration.
89 Successive Rejection Algorithm Sample every arm a once and let ˆµ t a be the average reward of arm a by time t; Let ˆµ t max = max a ˆµ t a and recall that α t = log(5nt 2 /δ)/t; Each arm a such that ˆµ t max ˆµ t a 2α t is removed from consideration. t = t + 1; Repeat till one arm left.
90 Graphical inaccurate representation 1 µ2 µ1 0 t
91 Generalizing to heavy tails In Bubeck, Cesa-Bianchi, Lugosi 2013, they develop log(1/δ) algorithms in regret settings when 1 + ɛ moments of each arm output are available.
92 Generalizing to heavy tails In Bubeck, Cesa-Bianchi, Lugosi 2013, they develop log(1/δ) algorithms in regret settings when 1 + ɛ moments of each arm output are available. Analysis again relies on forming a cone, which they do through truncation and clever usage of Bernstein inequality.
93 Generalizing to heavy tails In Bubeck, Cesa-Bianchi, Lugosi 2013, they develop log(1/δ) algorithms in regret settings when 1 + ɛ moments of each arm output are available. Analysis again relies on forming a cone, which they do through truncation and clever usage of Bernstein inequality. We perform some minor optimizations on their algorithm.
Ordinal optimization - Empirical large deviations rate estimators, and multi-armed bandit methods
Ordinal optimization - Empirical large deviations rate estimators, and multi-armed bandit methods Sandeep Juneja Tata Institute of Fundamental Research Mumbai, India joint work with Peter Glynn Applied
More informationStat 260/CS Learning in Sequential Decision Problems. Peter Bartlett
Stat 260/CS 294-102. Learning in Sequential Decision Problems. Peter Bartlett 1. Multi-armed bandit algorithms. Concentration inequalities. P(X ǫ) exp( ψ (ǫ))). Cumulant generating function bounds. Hoeffding
More informationMulti-armed bandit models: a tutorial
Multi-armed bandit models: a tutorial CERMICS seminar, March 30th, 2016 Multi-Armed Bandit model: general setting K arms: for a {1,..., K}, (X a,t ) t N is a stochastic process. (unknown distributions)
More informationRegret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems, Part I. Sébastien Bubeck Theory Group
Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems, Part I Sébastien Bubeck Theory Group i.i.d. multi-armed bandit, Robbins [1952] i.i.d. multi-armed bandit, Robbins [1952] Known
More informationThe information complexity of best-arm identification
The information complexity of best-arm identification Emilie Kaufmann, joint work with Olivier Cappé and Aurélien Garivier MAB workshop, Lancaster, January th, 206 Context: the multi-armed bandit model
More informationBandit models: a tutorial
Gdt COS, December 3rd, 2015 Multi-Armed Bandit model: general setting K arms: for a {1,..., K}, (X a,t ) t N is a stochastic process. (unknown distributions) Bandit game: a each round t, an agent chooses
More informationAdvanced Machine Learning
Advanced Machine Learning Bandit Problems MEHRYAR MOHRI MOHRI@ COURANT INSTITUTE & GOOGLE RESEARCH. Multi-Armed Bandit Problem Problem: which arm of a K-slot machine should a gambler pull to maximize his
More informationThe information complexity of sequential resource allocation
The information complexity of sequential resource allocation Emilie Kaufmann, joint work with Olivier Cappé, Aurélien Garivier and Shivaram Kalyanakrishan SMILE Seminar, ENS, June 8th, 205 Sequential allocation
More informationLecture 19: UCB Algorithm and Adversarial Bandit Problem. Announcements Review on stochastic multi-armed bandit problem
Lecture 9: UCB Algorithm and Adversarial Bandit Problem EECS598: Prediction and Learning: It s Only a Game Fall 03 Lecture 9: UCB Algorithm and Adversarial Bandit Problem Prof. Jacob Abernethy Scribe:
More informationOn the Complexity of Best Arm Identification with Fixed Confidence
On the Complexity of Best Arm Identification with Fixed Confidence Discrete Optimization with Noise Aurélien Garivier, Emilie Kaufmann COLT, June 23 th 2016, New York Institut de Mathématiques de Toulouse
More informationThe Multi-Armed Bandit Problem
The Multi-Armed Bandit Problem Electrical and Computer Engineering December 7, 2013 Outline 1 2 Mathematical 3 Algorithm Upper Confidence Bound Algorithm A/B Testing Exploration vs. Exploitation Scientist
More informationMultiple Identifications in Multi-Armed Bandits
Multiple Identifications in Multi-Armed Bandits arxiv:05.38v [cs.lg] 4 May 0 Sébastien Bubeck Department of Operations Research and Financial Engineering, Princeton University sbubeck@princeton.edu Tengyao
More informationTwo optimization problems in a stochastic bandit model
Two optimization problems in a stochastic bandit model Emilie Kaufmann joint work with Olivier Cappé, Aurélien Garivier and Shivaram Kalyanakrishnan Journées MAS 204, Toulouse Outline From stochastic optimization
More informationOn the Complexity of Best Arm Identification in Multi-Armed Bandit Models
On the Complexity of Best Arm Identification in Multi-Armed Bandit Models Aurélien Garivier Institut de Mathématiques de Toulouse Information Theory, Learning and Big Data Simons Institute, Berkeley, March
More informationStratégies bayésiennes et fréquentistes dans un modèle de bandit
Stratégies bayésiennes et fréquentistes dans un modèle de bandit thèse effectuée à Telecom ParisTech, co-dirigée par Olivier Cappé, Aurélien Garivier et Rémi Munos Journées MAS, Grenoble, 30 août 2016
More informationIntroduction to Bandit Algorithms. Introduction to Bandit Algorithms
Stochastic K-Arm Bandit Problem Formulation Consider K arms (actions) each correspond to an unknown distribution {ν k } K k=1 with values bounded in [0, 1]. At each time t, the agent pulls an arm I t {1,...,
More informationLecture 4: Lower Bounds (ending); Thompson Sampling
CMSC 858G: Bandits, Experts and Games 09/12/16 Lecture 4: Lower Bounds (ending); Thompson Sampling Instructor: Alex Slivkins Scribed by: Guowei Sun,Cheng Jie 1 Lower bounds on regret (ending) Recap from
More informationRegret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems. Sébastien Bubeck Theory Group
Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems Sébastien Bubeck Theory Group Part 1: i.i.d., adversarial, and Bayesian bandit models i.i.d. multi-armed bandit, Robbins [1952]
More informationSTAT 200C: High-dimensional Statistics
STAT 200C: High-dimensional Statistics Arash A. Amini May 30, 2018 1 / 59 Classical case: n d. Asymptotic assumption: d is fixed and n. Basic tools: LLN and CLT. High-dimensional setting: n d, e.g. n/d
More informationThe Multi-Arm Bandit Framework
The Multi-Arm Bandit Framework A. LAZARIC (SequeL Team @INRIA-Lille) ENS Cachan - Master 2 MVA SequeL INRIA Lille MVA-RL Course In This Lecture A. LAZARIC Reinforcement Learning Algorithms Oct 29th, 2013-2/94
More informationRevisiting the Exploration-Exploitation Tradeoff in Bandit Models
Revisiting the Exploration-Exploitation Tradeoff in Bandit Models joint work with Aurélien Garivier (IMT, Toulouse) and Tor Lattimore (University of Alberta) Workshop on Optimization and Decision-Making
More informationLecture 2: Review of Basic Probability Theory
ECE 830 Fall 2010 Statistical Signal Processing instructor: R. Nowak, scribe: R. Nowak Lecture 2: Review of Basic Probability Theory Probabilistic models will be used throughout the course to represent
More informationComputational Oracle Inequalities for Large Scale Model Selection Problems
for Large Scale Model Selection Problems University of California at Berkeley Queensland University of Technology ETH Zürich, September 2011 Joint work with Alekh Agarwal, John Duchi and Clément Levrard.
More informationSubsampling, Concentration and Multi-armed bandits
Subsampling, Concentration and Multi-armed bandits Odalric-Ambrym Maillard, R. Bardenet, S. Mannor, A. Baransi, N. Galichet, J. Pineau, A. Durand Toulouse, November 09, 2015 O-A. Maillard Subsampling and
More informationConcentration inequalities and tail bounds
Concentration inequalities and tail bounds John Duchi Outline I Basics and motivation 1 Law of large numbers 2 Markov inequality 3 Cherno bounds II Sub-Gaussian random variables 1 Definitions 2 Examples
More informationGeneralization theory
Generalization theory Daniel Hsu Columbia TRIPODS Bootcamp 1 Motivation 2 Support vector machines X = R d, Y = { 1, +1}. Return solution ŵ R d to following optimization problem: λ min w R d 2 w 2 2 + 1
More informationReinforcement Learning
Reinforcement Learning Lecture 5: Bandit optimisation Alexandre Proutiere, Sadegh Talebi, Jungseul Ok KTH, The Royal Institute of Technology Objectives of this lecture Introduce bandit optimisation: the
More informationLecture 3: Lower Bounds for Bandit Algorithms
CMSC 858G: Bandits, Experts and Games 09/19/16 Lecture 3: Lower Bounds for Bandit Algorithms Instructor: Alex Slivkins Scribed by: Soham De & Karthik A Sankararaman 1 Lower Bounds In this lecture (and
More informationLimiting Distributions
Limiting Distributions We introduce the mode of convergence for a sequence of random variables, and discuss the convergence in probability and in distribution. The concept of convergence leads us to the
More informationAn Optimal Bidimensional Multi Armed Bandit Auction for Multi unit Procurement
An Optimal Bidimensional Multi Armed Bandit Auction for Multi unit Procurement Satyanath Bhat Joint work with: Shweta Jain, Sujit Gujar, Y. Narahari Department of Computer Science and Automation, Indian
More informationPure Exploration Stochastic Multi-armed Bandits
C&A Workshop 2016, Hangzhou Pure Exploration Stochastic Multi-armed Bandits Jian Li Institute for Interdisciplinary Information Sciences Tsinghua University Outline Introduction 2 Arms Best Arm Identification
More informationProbability Background
Probability Background Namrata Vaswani, Iowa State University August 24, 2015 Probability recap 1: EE 322 notes Quick test of concepts: Given random variables X 1, X 2,... X n. Compute the PDF of the second
More informationTheory and Applications of Stochastic Systems Lecture Exponential Martingale for Random Walk
Instructor: Victor F. Araman December 4, 2003 Theory and Applications of Stochastic Systems Lecture 0 B60.432.0 Exponential Martingale for Random Walk Let (S n : n 0) be a random walk with i.i.d. increments
More informationDynamic resource allocation: Bandit problems and extensions
Dynamic resource allocation: Bandit problems and extensions Aurélien Garivier Institut de Mathématiques de Toulouse MAD Seminar, Université Toulouse 1 October 3rd, 2014 The Bandit Model Roadmap 1 The Bandit
More informationOnline Learning and Sequential Decision Making
Online Learning and Sequential Decision Making Emilie Kaufmann CNRS & CRIStAL, Inria SequeL, emilie.kaufmann@univ-lille.fr Research School, ENS Lyon, Novembre 12-13th 2018 Emilie Kaufmann Sequential Decision
More informationSelected Exercises on Expectations and Some Probability Inequalities
Selected Exercises on Expectations and Some Probability Inequalities # If E(X 2 ) = and E X a > 0, then P( X λa) ( λ) 2 a 2 for 0 < λ
More informationOn the Complexity of Best Arm Identification with Fixed Confidence
On the Complexity of Best Arm Identification with Fixed Confidence Discrete Optimization with Noise Aurélien Garivier, joint work with Emilie Kaufmann CNRS, CRIStAL) to be presented at COLT 16, New York
More informationMulti armed bandit problem: some insights
Multi armed bandit problem: some insights July 4, 20 Introduction Multi Armed Bandit problems have been widely studied in the context of sequential analysis. The application areas include clinical trials,
More informationComplexity of two and multi-stage stochastic programming problems
Complexity of two and multi-stage stochastic programming problems A. Shapiro School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, Georgia 30332-0205, USA The concept
More informationBayesian and Frequentist Methods in Bandit Models
Bayesian and Frequentist Methods in Bandit Models Emilie Kaufmann, Telecom ParisTech Bayes In Paris, ENSAE, October 24th, 2013 Emilie Kaufmann (Telecom ParisTech) Bayesian and Frequentist Bandits BIP,
More informationConcentration inequalities and the entropy method
Concentration inequalities and the entropy method Gábor Lugosi ICREA and Pompeu Fabra University Barcelona what is concentration? We are interested in bounding random fluctuations of functions of many
More informationExercises and Answers to Chapter 1
Exercises and Answers to Chapter The continuous type of random variable X has the following density function: a x, if < x < a, f (x), otherwise. Answer the following questions. () Find a. () Obtain mean
More informationarxiv: v2 [stat.ml] 14 Nov 2016
Journal of Machine Learning Research 6 06-4 Submitted 7/4; Revised /5; Published /6 On the Complexity of Best-Arm Identification in Multi-Armed Bandit Models arxiv:407.4443v [stat.ml] 4 Nov 06 Emilie Kaufmann
More informationThe No-Regret Framework for Online Learning
The No-Regret Framework for Online Learning A Tutorial Introduction Nahum Shimkin Technion Israel Institute of Technology Haifa, Israel Stochastic Processes in Engineering IIT Mumbai, March 2013 N. Shimkin,
More informationStat 260/CS Learning in Sequential Decision Problems.
Stat 260/CS 294-102. Learning in Sequential Decision Problems. Peter Bartlett 1. Multi-armed bandit algorithms. Exponential families. Cumulant generating function. KL-divergence. KL-UCB for an exponential
More informationNearly Optimal Sampling Algorithms for Combinatorial Pure Exploration
JMLR: Workshop and Conference Proceedings vol 65: 55, 207 30th Annual Conference on Learning Theory Nearly Optimal Sampling Algorithms for Combinatorial Pure Exploration Editor: Under Review for COLT 207
More informationEASINESS IN BANDITS. Gergely Neu. Pompeu Fabra University
EASINESS IN BANDITS Gergely Neu Pompeu Fabra University EASINESS IN BANDITS Gergely Neu Pompeu Fabra University THE BANDIT PROBLEM Play for T rounds attempting to maximize rewards THE BANDIT PROBLEM Play
More informationAdaptive Concentration Inequalities for Sequential Decision Problems
Adaptive Concentration Inequalities for Sequential Decision Problems Shengjia Zhao Tsinghua University zhaosj12@stanford.edu Ashish Sabharwal Allen Institute for AI AshishS@allenai.org Enze Zhou Tsinghua
More informationBandit Algorithms for Pure Exploration: Best Arm Identification and Game Tree Search. Wouter M. Koolen
Bandit Algorithms for Pure Exploration: Best Arm Identification and Game Tree Search Wouter M. Koolen Machine Learning and Statistics for Structures Friday 23 rd February, 2018 Outline 1 Intro 2 Model
More informationGrundlagen der Künstlichen Intelligenz
Grundlagen der Künstlichen Intelligenz Uncertainty & Probabilities & Bandits Daniel Hennes 16.11.2017 (WS 2017/18) University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Uncertainty Probability
More informationPure Exploration Stochastic Multi-armed Bandits
CAS2016 Pure Exploration Stochastic Multi-armed Bandits Jian Li Institute for Interdisciplinary Information Sciences Tsinghua University Outline Introduction Optimal PAC Algorithm (Best-Arm, Best-k-Arm):
More informationAn Estimation Based Allocation Rule with Super-linear Regret and Finite Lock-on Time for Time-dependent Multi-armed Bandit Processes
An Estimation Based Allocation Rule with Super-linear Regret and Finite Lock-on Time for Time-dependent Multi-armed Bandit Processes Prokopis C. Prokopiou, Peter E. Caines, and Aditya Mahajan McGill University
More informationBandits : optimality in exponential families
Bandits : optimality in exponential families Odalric-Ambrym Maillard IHES, January 2016 Odalric-Ambrym Maillard Bandits 1 / 40 Introduction 1 Stochastic multi-armed bandits 2 Boundary crossing probabilities
More informationStochastic bandits: Explore-First and UCB
CSE599s, Spring 2014, Online Learning Lecture 15-2/19/2014 Stochastic bandits: Explore-First and UCB Lecturer: Brendan McMahan or Ofer Dekel Scribe: Javad Hosseini In this lecture, we like to answer this
More informationLimiting Distributions
We introduce the mode of convergence for a sequence of random variables, and discuss the convergence in probability and in distribution. The concept of convergence leads us to the two fundamental results
More informationEfficient rare-event simulation for sums of dependent random varia
Efficient rare-event simulation for sums of dependent random variables Leonardo Rojas-Nandayapa joint work with José Blanchet February 13, 2012 MCQMC UNSW, Sydney, Australia Contents Introduction 1 Introduction
More informationFast Rates for Estimation Error and Oracle Inequalities for Model Selection
Fast Rates for Estimation Error and Oracle Inequalities for Model Selection Peter L. Bartlett Computer Science Division and Department of Statistics University of California, Berkeley bartlett@cs.berkeley.edu
More informationStatistics 300B Winter 2018 Final Exam Due 24 Hours after receiving it
Statistics 300B Winter 08 Final Exam Due 4 Hours after receiving it Directions: This test is open book and open internet, but must be done without consulting other students. Any consultation of other students
More informationMaster s Written Examination
Master s Written Examination Option: Statistics and Probability Spring 016 Full points may be obtained for correct answers to eight questions. Each numbered question which may have several parts is worth
More informationLecture 7 Introduction to Statistical Decision Theory
Lecture 7 Introduction to Statistical Decision Theory I-Hsiang Wang Department of Electrical Engineering National Taiwan University ihwang@ntu.edu.tw December 20, 2016 1 / 55 I-Hsiang Wang IT Lecture 7
More information1 MDP Value Iteration Algorithm
CS 0. - Active Learning Problem Set Handed out: 4 Jan 009 Due: 9 Jan 009 MDP Value Iteration Algorithm. Implement the value iteration algorithm given in the lecture. That is, solve Bellman s equation using
More informationLecture 4: September Reminder: convergence of sequences
36-705: Intermediate Statistics Fall 2017 Lecturer: Siva Balakrishnan Lecture 4: September 6 In this lecture we discuss the convergence of random variables. At a high-level, our first few lectures focused
More informationMulti-Armed Bandit Formulations for Identification and Control
Multi-Armed Bandit Formulations for Identification and Control Cristian R. Rojas Joint work with Matías I. Müller and Alexandre Proutiere KTH Royal Institute of Technology, Sweden ERNSI, September 24-27,
More information6.1 Moment Generating and Characteristic Functions
Chapter 6 Limit Theorems The power statistics can mostly be seen when there is a large collection of data points and we are interested in understanding the macro state of the system, e.g., the average,
More informationIntroduction to Reinforcement Learning Part 3: Exploration for decision making, Application to games, optimization, and planning
Introduction to Reinforcement Learning Part 3: Exploration for decision making, Application to games, optimization, and planning Rémi Munos SequeL project: Sequential Learning http://researchers.lille.inria.fr/
More informationAnalysis of Thompson Sampling for the multi-armed bandit problem
Analysis of Thompson Sampling for the multi-armed bandit problem Shipra Agrawal Microsoft Research India shipra@microsoft.com Navin Goyal Microsoft Research India navingo@microsoft.com Abstract The multi-armed
More informationTractable Sampling Strategies for Ordinal Optimization
Submitted to Operations Research manuscript Please, provide the manuscript number!) Authors are encouraged to submit new papers to INFORMS journals by means of a style file template, which includes the
More informationLecture 1: August 28
36-705: Intermediate Statistics Fall 2017 Lecturer: Siva Balakrishnan Lecture 1: August 28 Our broad goal for the first few lectures is to try to understand the behaviour of sums of independent random
More informationAn Empirical Algorithm for Relative Value Iteration for Average-cost MDPs
2015 IEEE 54th Annual Conference on Decision and Control CDC December 15-18, 2015. Osaka, Japan An Empirical Algorithm for Relative Value Iteration for Average-cost MDPs Abhishek Gupta Rahul Jain Peter
More informationLearning Methods for Online Prediction Problems. Peter Bartlett Statistics and EECS UC Berkeley
Learning Methods for Online Prediction Problems Peter Bartlett Statistics and EECS UC Berkeley Course Synopsis A finite comparison class: A = {1,..., m}. Converting online to batch. Online convex optimization.
More informationFall 2017 STAT 532 Homework Peter Hoff. 1. Let P be a probability measure on a collection of sets A.
1. Let P be a probability measure on a collection of sets A. (a) For each n N, let H n be a set in A such that H n H n+1. Show that P (H n ) monotonically converges to P ( k=1 H k) as n. (b) For each n
More informationProceedings of the 2016 Winter Simulation Conference T. M. K. Roeder, P. I. Frazier, R. Szechtman, E. Zhou, T. Huschka, and S. E. Chick, eds.
Proceedings of the 2016 Winter Simulation Conference T. M. K. Roeder, P. I. Frazier, R. Szechtman, E. Zhou, T. Huscha, and S. E. Chic, eds. OPTIMAL COMPUTING BUDGET ALLOCATION WITH EXPONENTIAL UNDERLYING
More informationSTAT 200C: High-dimensional Statistics
STAT 200C: High-dimensional Statistics Arash A. Amini April 27, 2018 1 / 80 Classical case: n d. Asymptotic assumption: d is fixed and n. Basic tools: LLN and CLT. High-dimensional setting: n d, e.g. n/d
More informationCsaba Szepesvári 1. University of Alberta. Machine Learning Summer School, Ile de Re, France, 2008
LEARNING THEORY OF OPTIMAL DECISION MAKING PART I: ON-LINE LEARNING IN STOCHASTIC ENVIRONMENTS Csaba Szepesvári 1 1 Department of Computing Science University of Alberta Machine Learning Summer School,
More informationProblem 1 (20) Log-normal. f(x) Cauchy
ORF 245. Rigollet Date: 11/21/2008 Problem 1 (20) f(x) f(x) 0.0 0.1 0.2 0.3 0.4 0.0 0.2 0.4 0.6 0.8 4 2 0 2 4 Normal (with mean -1) 4 2 0 2 4 Negative-exponential x x f(x) f(x) 0.0 0.1 0.2 0.3 0.4 0.5
More informationBandit Algorithms. Tor Lattimore & Csaba Szepesvári
Bandit Algorithms Tor Lattimore & Csaba Szepesvári Bandits Time 1 2 3 4 5 6 7 8 9 10 11 12 Left arm $1 $0 $1 $1 $0 Right arm $1 $0 Five rounds to go. Which arm would you play next? Overview What are bandits,
More informationInferring from data. Theory of estimators
Inferring from data Theory of estimators 1 Estimators Estimator is any function of the data e(x) used to provide an estimate ( a measurement ) of an unknown parameter. Because estimators are functions
More informationStochastic Contextual Bandits with Known. Reward Functions
Stochastic Contextual Bandits with nown 1 Reward Functions Pranav Sakulkar and Bhaskar rishnamachari Ming Hsieh Department of Electrical Engineering Viterbi School of Engineering University of Southern
More informationAdaptive Concentration Inequalities for Sequential Decision Problems
Adaptive Concentration Inequalities for Sequential Decision Problems Shengjia Zhao Tsinghua University zhaosj12@stanford.edu Ashish Sabharwal Allen Institute for AI AshishS@allenai.org Enze Zhou Tsinghua
More informationStat 260/CS Learning in Sequential Decision Problems. Peter Bartlett
Stat 260/CS 294-102. Learning in Sequential Decision Problems. Peter Bartlett 1. Adversarial bandits Definition: sequential game. Lower bounds on regret from the stochastic case. Exp3: exponential weights
More information1 Review of Probability
1 Review of Probability Random variables are denoted by X, Y, Z, etc. The cumulative distribution function (c.d.f.) of a random variable X is denoted by F (x) = P (X x), < x
More informationConcentration of Measures by Bounded Couplings
Concentration of Measures by Bounded Couplings Subhankar Ghosh, Larry Goldstein and Ümit Işlak University of Southern California [arxiv:0906.3886] [arxiv:1304.5001] May 2013 Concentration of Measure Distributional
More informationLecture 22: Variance and Covariance
EE5110 : Probability Foundations for Electrical Engineers July-November 2015 Lecture 22: Variance and Covariance Lecturer: Dr. Krishna Jagannathan Scribes: R.Ravi Kiran In this lecture we will introduce
More informationSTAT 450. Moment Generating Functions
STAT 450 Moment Generating Functions There are many uses of generating functions in mathematics. We often study the properties of a sequence a n of numbers by creating the function a n s n n0 In statistics
More informationis a Borel subset of S Θ for each c R (Bertsekas and Shreve, 1978, Proposition 7.36) This always holds in practical applications.
Stat 811 Lecture Notes The Wald Consistency Theorem Charles J. Geyer April 9, 01 1 Analyticity Assumptions Let { f θ : θ Θ } be a family of subprobability densities 1 with respect to a measure µ on a measurable
More informationINTRODUCTION TO INTERSECTION-UNION TESTS
INTRODUCTION TO INTERSECTION-UNION TESTS Jimmy A. Doi, Cal Poly State University San Luis Obispo Department of Statistics (jdoi@calpoly.edu Key Words: Intersection-Union Tests; Multiple Comparisons; Acceptance
More informationThe Multi-Armed Bandit Problem
Università degli Studi di Milano The bandit problem [Robbins, 1952]... K slot machines Rewards X i,1, X i,2,... of machine i are i.i.d. [0, 1]-valued random variables An allocation policy prescribes which
More informationIntroduction to Reinforcement Learning Part 3: Exploration for sequential decision making
Introduction to Reinforcement Learning Part 3: Exploration for sequential decision making Rémi Munos SequeL project: Sequential Learning http://researchers.lille.inria.fr/ munos/ INRIA Lille - Nord Europe
More informationProbability inequalities 11
Paninski, Intro. Math. Stats., October 5, 2005 29 Probability inequalities 11 There is an adage in probability that says that behind every limit theorem lies a probability inequality (i.e., a bound on
More informationCase study: stochastic simulation via Rademacher bootstrap
Case study: stochastic simulation via Rademacher bootstrap Maxim Raginsky December 4, 2013 In this lecture, we will look at an application of statistical learning theory to the problem of efficient stochastic
More informationAdvanced Topics in Machine Learning and Algorithmic Game Theory Fall semester, 2011/12
Advanced Topics in Machine Learning and Algorithmic Game Theory Fall semester, 2011/12 Lecture 4: Multiarmed Bandit in the Adversarial Model Lecturer: Yishay Mansour Scribe: Shai Vardi 4.1 Lecture Overview
More informationHoeffding, Chernoff, Bennet, and Bernstein Bounds
Stat 928: Statistical Learning Theory Lecture: 6 Hoeffding, Chernoff, Bennet, Bernstein Bounds Instructor: Sham Kakade 1 Hoeffding s Bound We say X is a sub-gaussian rom variable if it has quadratically
More informationReward Maximization Under Uncertainty: Leveraging Side-Observations on Networks
Reward Maximization Under Uncertainty: Leveraging Side-Observations Reward Maximization Under Uncertainty: Leveraging Side-Observations on Networks Swapna Buccapatnam AT&T Labs Research, Middletown, NJ
More informationOn Bayesian bandit algorithms
On Bayesian bandit algorithms Emilie Kaufmann joint work with Olivier Cappé, Aurélien Garivier, Nathaniel Korda and Rémi Munos July 1st, 2012 Emilie Kaufmann (Telecom ParisTech) On Bayesian bandit algorithms
More informationAPPM/MATH 4/5520 Solutions to Exam I Review Problems. f X 1,X 2. 2e x 1 x 2. = x 2
APPM/MATH 4/5520 Solutions to Exam I Review Problems. (a) f X (x ) f X,X 2 (x,x 2 )dx 2 x 2e x x 2 dx 2 2e 2x x was below x 2, but when marginalizing out x 2, we ran it over all values from 0 to and so
More informationarxiv: v4 [stat.me] 20 Oct 2017
A simple method for implementing Monte Carlo tests Dong Ding, Axel Gandy, and Georg Hahn Department of Mathematics, Imperial College London arxiv:1611.01675v4 [stat.me] 20 Oct 2017 Abstract We consider
More informationPart IA Probability. Theorems. Based on lectures by R. Weber Notes taken by Dexter Chua. Lent 2015
Part IA Probability Theorems Based on lectures by R. Weber Notes taken by Dexter Chua Lent 2015 These notes are not endorsed by the lecturers, and I have modified them (often significantly) after lectures.
More informationLearning, Games, and Networks
Learning, Games, and Networks Abhishek Sinha Laboratory for Information and Decision Systems MIT ML Talk Series @CNRG December 12, 2016 1 / 44 Outline 1 Prediction With Experts Advice 2 Application to
More informationApproximation of Heavy-tailed distributions via infinite dimensional phase type distributions
1 / 36 Approximation of Heavy-tailed distributions via infinite dimensional phase type distributions Leonardo Rojas-Nandayapa The University of Queensland ANZAPW March, 2015. Barossa Valley, SA, Australia.
More informationMulti-Armed Bandits. Credit: David Silver. Google DeepMind. Presenter: Tianlu Wang
Multi-Armed Bandits Credit: David Silver Google DeepMind Presenter: Tianlu Wang Credit: David Silver (DeepMind) Multi-Armed Bandits Presenter: Tianlu Wang 1 / 27 Outline 1 Introduction Exploration vs.
More information