Full-information Online Learning
|
|
- Emerald Griffin
- 6 years ago
- Views:
Transcription
1 Introduction Expert Advice OCO LM A DA NANJING UNIVERSITY Full-information Lijun Zhang Nanjing University, China June 2, 2017
2 Outline Introduction Expert Advice OCO 1 Introduction Definitions Regret 2 Prediction with Expert Advice 3 Online Convex Optimization Convex Functions Strongly Convex Functions Exponentially Concave Functions
3 Outline Introduction Expert Advice OCO Definitions Regret 1 Introduction Definitions Regret 2 Prediction with Expert Advice 3 Online Convex Optimization Convex Functions Strongly Convex Functions Exponentially Concave Functions
4 Introduction Expert Advice OCO Definitions Regret What Happens in an Internet Minute?
5 Outline Introduction Expert Advice OCO Definitions Regret 1 Introduction Definitions Regret 2 Prediction with Expert Advice 3 Online Convex Optimization Convex Functions Strongly Convex Functions Exponentially Concave Functions
6 Introduction Expert Advice OCO Definitions Regret Online Algorithm vs Online Algorithm [Karp, 1992] An online algorithm is one that receives a sequence of requests and performs an immediate action in response to each request. [Shalev-Shwartz, 2011] Online learning is the process of answering a sequence of questions given (maybe partial) knowledge of answers to previous questions and possibly additional information.
7 Introduction Expert Advice OCO Definitions Regret Online Algorithm vs Online Algorithm [Karp, 1992] An online algorithm is one that receives a sequence of requests and performs an immediate action in response to each request. Computer Vision, Machine Learning, Data Mining Theoretical Computer Science, Computer Networks [Shalev-Shwartz, 2011] Online learning is the process of answering a sequence of questions given (maybe partial) knowledge of answers to previous questions and possibly additional information.
8 Introduction Expert Advice OCO Definitions Regret Online Algorithm vs Online Algorithm [Karp, 1992] An online algorithm is one that receives a sequence of requests and performs an immediate action in response to each request. Computer Vision, Machine Learning, Data Mining Theoretical Computer Science, Computer Networks [Shalev-Shwartz, 2011] Online learning is the process of answering a sequence of questions given (maybe partial) knowledge of answers to previous questions and possibly additional information. Machine Learning, Game Theory, Information Theory
9 Introduction Expert Advice OCO Definitions Regret Online Algorithm vs Online Algorithm [Karp, 1992] An online algorithm is one that receives a sequence of requests and performs an immediate action in response to each request. The Ski Rental Problem: in the t-th day Rent (1$) or Buy (10$)? [Shalev-Shwartz, 2011] Online learning is the process of answering a sequence of questions given (maybe partial) knowledge of answers to previous questions and possibly additional information.
10 Introduction Expert Advice OCO Definitions Regret Online Algorithm vs Online Algorithm [Karp, 1992] An online algorithm is one that receives a sequence of requests and performs an immediate action in response to each request. The Ski Rental Problem: in the t-th day Rent (1$) or Buy (10$)? [Shalev-Shwartz, 2011] Online learning is the process of answering a sequence of questions given (maybe partial) knowledge of answers to previous questions and possibly additional information. Online Classification: in the t-th round Recevie x t R d, predict ŷ t, observe y t
11 Introduction Expert Advice OCO Definitions Regret Full-information vs Bandit [Shalev-Shwartz, 2011] Online learning is the process of answering a sequence of questions given (maybe partial) knowledge of answers to previous questions and possibly additional information.
12 Introduction Expert Advice OCO Definitions Regret Full-information vs Bandit [Shalev-Shwartz, 2011] Online learning is the process of answering a sequence of questions given (maybe partial) knowledge of answers to previous questions and possibly additional information. Full-information
13 Introduction Expert Advice OCO Definitions Regret Full-information vs Bandit [Shalev-Shwartz, 2011] Online learning is the process of answering a sequence of questions given (maybe partial) knowledge of answers to previous questions and possibly additional information. Bandit
14 Introduction Expert Advice OCO Definitions Regret Formal Definitions 1: for t = 1, 2,...,T do 4: end for
15 Introduction Expert Advice OCO Definitions Regret Formal Definitions 1: for t = 1, 2,...,T do 2: Learner picks a decision w t W Adversary chooses a function f t ( ) 4: end for A classifier Learner An example A loss Adversary
16 Introduction Expert Advice OCO Definitions Regret Formal Definitions 1: for t = 1, 2,...,T do 2: Learner picks a decision w t W Adversary chooses a function f t ( ) 3: Learner suffers loss f t (w t ) and updates w t 4: end for A classifier Learner An example A loss Adversary Suffer and update
17 Introduction Expert Advice OCO Definitions Regret Formal Definitions 1: for t = 1, 2,...,T do 2: Learner picks a decision w t W Adversary chooses a function f t ( ) 3: Learner suffers loss f t (w t ) and updates w t 4: end for Cumulative Loss Cumulative Loss = f t (w t )
18 Introduction Expert Advice OCO Definitions Regret Formal Definitions 1: for t = 1, 2,...,T do 2: Learner picks a decision w t W Adversary chooses a function f t ( ) 3: Learner suffers loss f t (w t ) and updates w t 4: end for Cumulative Loss Cumulative Loss = f t (w t ) Full-information Learner observes the function f t ( ) Online first-order optimization Bandit Learner only observes the value of f t (w t ) Online zero-order optimization
19 Outline Introduction Expert Advice OCO Definitions Regret 1 Introduction Definitions Regret 2 Prediction with Expert Advice 3 Online Convex Optimization Convex Functions Strongly Convex Functions Exponentially Concave Functions
20 Regret Introduction Expert Advice OCO Definitions Regret Cumulative Loss Cumulative Loss = f t (w t )
21 Regret Introduction Expert Advice OCO Definitions Regret Cumulative Loss Regret Regret = Cumulative Loss = f t (w t ) f t (w t ) min w W f t (w)
22 Regret Introduction Expert Advice OCO Definitions Regret Cumulative Loss Cumulative Loss = f t (w t ) Regret Regret = f t (w t ) }{{} Cumulative Loss of Online Learner min w W f t (w) }{{} Minimal Loss of Batch Learner
23 Regret Introduction Expert Advice OCO Definitions Regret Cumulative Loss Cumulative Loss = f t (w t ) Regret Regret = f t (w t ) }{{} Cumulative Loss of Online Learner min w W f t (w) }{{} Minimal Loss of Batch Learner Hannan Consistent ( ) 1 lim sup f t (w t ) min f t (w) = 0, with probability 1 T T w W
24 Regret Introduction Expert Advice OCO Definitions Regret Cumulative Loss Cumulative Loss = f t (w t ) Regret Regret = f t (w t ) }{{} Cumulative Loss of Online Learner min w W f t (w) }{{} Minimal Loss of Batch Learner Hannan Consistent f t (w t ) min f t (w) = o(t), with probability 1 w W
25 Outline Introduction Expert Advice OCO 1 Introduction Definitions Regret 2 Prediction with Expert Advice 3 Online Convex Optimization Convex Functions Strongly Convex Functions Exponentially Concave Functions
26 Introduction Expert Advice OCO Definitions The Prediction Protocol 1: for t = 1,...,T do 7: end for
27 Introduction Expert Advice OCO Definitions The Prediction Protocol 1: for t = 1,...,T do 2: The environment chooses the next outcome y t and the expert advice {f i,t : i [N]} 7: end for
28 Introduction Expert Advice OCO Definitions The Prediction Protocol 1: for t = 1,...,T do 2: The environment chooses the next outcome y t and the expert advice {f i,t : i [N]} 3: The expert advice is revealed to the forecaster 7: end for
29 Introduction Expert Advice OCO Definitions The Prediction Protocol 1: for t = 1,...,T do 2: The environment chooses the next outcome y t and the expert advice {f i,t : i [N]} 3: The expert advice is revealed to the forecaster 4: The forecaster chooses the prediction ˆp t 7: end for
30 Introduction Expert Advice OCO Definitions The Prediction Protocol 1: for t = 1,...,T do 2: The environment chooses the next outcome y t and the expert advice {f i,t : i [N]} 3: The expert advice is revealed to the forecaster 4: The forecaster chooses the prediction ˆp t 5: The environment reveals the next outcome y t 7: end for
31 Introduction Expert Advice OCO Definitions The Prediction Protocol 1: for t = 1,...,T do 2: The environment chooses the next outcome y t and the expert advice {f i,t : i [N]} 3: The expert advice is revealed to the forecaster 4: The forecaster chooses the prediction ˆp t 5: The environment reveals the next outcome y t 6: The forecaster incurs loss l(ˆp t, y t ) and each expert i incurs loss l(f i,t, y t ) 7: end for
32 Introduction Expert Advice OCO Definitions The Prediction Protocol 1: for t = 1,...,T do 2: The environment chooses the next outcome y t and the expert advice {f i,t : i [N]} 3: The expert advice is revealed to the forecaster 4: The forecaster chooses the prediction ˆp t 5: The environment reveals the next outcome y t 6: The forecaster incurs loss l(ˆp t, y t ) and each expert i incurs loss l(f i,t, y t ) 7: end for Regret with respect to expect i ( R i,t = l( p t, y t ) l(f i,t, y t ) ) = L T L i,t
33 Introduction Expert Advice OCO Online Algorithms Weighted Average Prediction N i=1 p t = w i,t 1f i,t N j=1 w j,t 1 where w i,t 1 is the weight assigned to expert i
34 Introduction Expert Advice OCO Online Algorithms Weighted Average Prediction N i=1 p t = w i,t 1f i,t N j=1 w j,t 1 where w i,t 1 is the weight assigned to expert i and Polynomially Weighted Average Forecaster w i,t 1 = 2(R i,t 1) p 1 + (R t 1 ) + p 2 p p t = N t 1 ( i=1( s=1 l( p s, y s ) l(f i,s, y s ) )) p 1 ( l( p s, y s ) l(f j,s, y s ) )) p 1 N j=1( t 1 s=1 + f i,t +
35 Introduction Expert Advice OCO Online Algorithms Weighted Average Prediction N i=1 p t = w i,t 1f i,t N j=1 w j,t 1 where w i,t 1 is the weight assigned to expert i Exponentially Weighted Average Forecaster w i,t 1 = e ηr i,t 1 N j=1 eηr j,t 1 and p t = ( ) N i=1 exp η( L t 1 L i,t 1 ) f i,t ( ) = N j=1 exp η( L t 1 L j,t 1 ) N i=1 e ηl i,t 1f i,t N j=1 e ηl j,t 1
36 Introduction Expert Advice OCO Regret Bounds I Corollary 2.1 of [Cesa-Bianchi and Lugosi, 2006] Assume that the loss function l is convex in its first argument and that it takes values in [0, 1]. Then, for any sequence y 1, y 2,... of outcomes and for any T 1, the regret of the polynomially weighted average forecaster satisfies L T min i=1,...,n L i,t T(p 1)N 2/p
37 Introduction Expert Advice OCO Regret Bounds I Corollary 2.1 of [Cesa-Bianchi and Lugosi, 2006] Assume that the loss function l is convex in its first argument and that it takes values in [0, 1]. Then, for any sequence y 1, y 2,... of outcomes and for any T 1, the regret of the polynomially weighted average forecaster satisfies L T min i=1,...,n L i,t T(p 1)N 2/p When p = 2, we have L T min i=1,...,n L i,t TN When p = 2ln N, we have L T min i=1,...,n L i,t Te(2ln N 1)
38 Introduction Expert Advice OCO Regret Bounds II Corollary 2.2 of [Cesa-Bianchi and Lugosi, 2006] Assume that the loss function l is convex in its first argument and that it takes values in [0, 1]. Then, for any sequence y 1, y 2,... of outcomes and for any T 1, the regret of the exponentially weighted average forecaster satisfies L T min L i,t ln N i=1,...,n η + ηt 2
39 Introduction Expert Advice OCO Regret Bounds II Corollary 2.2 of [Cesa-Bianchi and Lugosi, 2006] Assume that the loss function l is convex in its first argument and that it takes values in [0, 1]. Then, for any sequence y 1, y 2,... of outcomes and for any T 1, the regret of the exponentially weighted average forecaster satisfies L T min L i,t ln N i=1,...,n η + ηt 2 When η = 2ln N/T, we have L T min i=1,...,n L i,t 2T ln N
40 Introduction Expert Advice OCO Extensions Tighter Regret Bounds Small Losses L T min L i,t i=1,...,n where L T = min i=1,...,n L i,t Exp-concave Losses 2L T ln N +ln N L T min i=1,...,n L i,t ln N η
41 Introduction Expert Advice OCO Extensions Tighter Regret Bounds Small Losses L T min L i,t i=1,...,n where L T = min i=1,...,n L i,t Exp-concave Losses 2L T ln N +ln N L T min i=1,...,n L i,t ln N η Tracking Regret ( R(i 1,...,i T ) = l( p t, y t ) l(f it,t, y t ) )
42 Outline Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co 1 Introduction Definitions Regret 2 Prediction with Expert Advice 3 Online Convex Optimization Convex Functions Strongly Convex Functions Exponentially Concave Functions
43 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Definitions Online Convex Optimization 1: for t = 1, 2,...,T do 2: Learner picks a decision w t W Adversary chooses a function f t ( ) 3: Learner suffers loss f t (w t ) and updates w t 4: end for where W and f t s are convex
44 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Definitions Online Convex Optimization 1: for t = 1, 2,...,T do 2: Learner picks a decision w t W Adversary chooses a function f t ( ) 3: Learner suffers loss f t (w t ) and updates w t 4: end for where W and f t s are convex Online Gradient Descent w t+1 = Π W (w t η t f t (w t )) where Π W ( ) is the projection operator
45 Outline Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co 1 Introduction Definitions Regret 2 Prediction with Expert Advice 3 Online Convex Optimization Convex Functions Strongly Convex Functions Exponentially Concave Functions
46 Analysis I Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Define w t+1 = w t η t f t (w t ). For any w W, we have f t (w t ) f t (w) f t (w t ), w t w = 1 η t w t w t+1, w t w = 1 ( wt w 2 2 w t+1 w w t w 2η t+1 2 ) 2 t = 1 2η t ( wt w 2 2 w t+1 w η t ( wt w 2 2 w t+1 w 2 2 By adding the inequalities of all iterations, we have f t (w t ) f t (w) 1 2η 1 w 1 w η T w T+1 w t=2 ( 1 1 ) w t w η t η t 1 2 ) η t + 2 f t(w t ) 2 2 ) η t + 2 f t(w t ) 2 2 η t f t (w t ) 2 2
47 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Analysis II Assuming we have By setting η t η t 1, w t w 2 2 D 2, and f t (w t ) 2 2 G 2, f t (w t ) f t (w) D2 + D2 2η 1 2 = D2 + G2 2η T 2 t=2 η t = 1 t, ( 1 1 )+ G2 η t η t 1 2 η t η t we have f t (w t ) f t (w) ( ) D 2 T 2 + G2
48 Outline Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co 1 Introduction Definitions Regret 2 Prediction with Expert Advice 3 Online Convex Optimization Convex Functions Strongly Convex Functions Exponentially Concave Functions
49 Analysis I Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Define w t+1 = w t η t f t (w t ). For any w W, we have f t (w t ) f t (w) f t (w t ), w t w λ 2 w t w ( wt w 2 2 w t+1 w 2 ) η t 2 + 2η t 2 f t(w t ) 2 2 λ 2 w t w 2 2 By adding the inequalities of all iterations, we have f t (w t ) f t (w) 1 2η 1 w 1 w 2 2 λ 2 w 1 w η T w T+1 w t=2 ( 1 1 ) λ w t w η t η t 1 2 η t f t (w t ) 2 2
50 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Analysis II Assuming we have f t (w t ) 2 2 G 2, f t (w t ) f t (w) 1 2η 1 w 1 w 2 2 λ 2 w 1 w 2 2 By setting we have t=2 ( 1 1 λ ) w t w 22 + G2 η t η t 1 2 η t = 1 λt, η t f t (w t ) f t (w) G2 2λ 1 t G2 (log T + 1) 2λ
51 Outline Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co 1 Introduction Definitions Regret 2 Prediction with Expert Advice 3 Online Convex Optimization Convex Functions Strongly Convex Functions Exponentially Concave Functions
52 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Definitions Exponential Concavity A function f( ) : W R is α-exp-concave if exp( αf( )) is concave over W.
53 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Definitions Exponential Concavity A function f( ) : W R is α-exp-concave if exp( αf( )) is concave over W. Logistic Loss Square Loss Negative Logarithm Loss ( ) f(w) = log 1+exp( yx w) f(w) = (x w y) 2 f(w) = log(x w)
54 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Online Newton Step The Algorithm 1: A 1 = 1 β 2 D 2 I 2: for t = 1, 2,...,T do 3: A t+1 = A t + f t (w t )[ f t (w t )] 4: w t+1 =Π A t W =argmin w W ( w t 1 β A 1 where w t+1 = w t 1 β A 1 t f t (w t ) 5: end for ) t f t (w t ) ( w w t+1 ) At ( w w t+1 )
55 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Regret Bound Theorem 2 of [Hazan et al., 2007] Assume that for all t, the loss function f t : W R d R is α-exp-concave and has the property that f t (w) 2 G, w W, t [T] Then, online Newton Step with β = 1 { } 1 2 min 4GD,α has the following regret bound ( ) 1 f t (w t ) min f t (w) 5 w W α + GD d log T
56 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Online-to-batch Conversion Statistical Assumption f 1, f 2,... are sampled independently from P Define F(w) = E f P [f(w)]
57 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Online-to-batch Conversion Statistical Assumption f 1, f 2,... are sampled independently from P Define F(w) = E f P [f(w)] Regret Bound f t (w t ) f t (w) C Taking expectation over both sides, we have [ ] E F(w t ) F(w) C
58 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Online-to-batch Conversion Statistical Assumption f 1, f 2,... are sampled independently from P Define F(w) = E f P [f(w)] Regret Bound f t (w t ) f t (w) C Taking expectation over both sides, we have [ ] E F(w t ) F(w) C Risk Bound E[F( w)] F(w) C T, where w = 1 T w t
59 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Examples of Conversion Convex Functions E[F( w)] F(w) 1 ( ) D 2 T 2 + G2 High-probability Bound [Cesa-bianchi et al., 2002]
60 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Examples of Conversion Convex Functions E[F( w)] F(w) 1 ( ) D 2 T 2 + G2 High-probability Bound [Cesa-bianchi et al., 2002] Strongly Convex Functions E[F( w)] F(w) G2 (log T + 1) 2λT High-probability Bound [Kakade and Tewari, 2009]
61 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Examples of Conversion Convex Functions E[F( w)] F(w) 1 ( ) D 2 T 2 + G2 High-probability Bound [Cesa-bianchi et al., 2002] Strongly Convex Functions E[F( w)] F(w) G2 (log T + 1) 2λT High-probability Bound [Kakade and Tewari, 2009] Exponentially Concave Functions ( ) 1 d log T E[F( w)] F(w) 5 α + GD T High-probability Bound [Mahdavi et al., 2015]
62 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Extensions Faster Rates [Srebro et al., 2010] f t (w t ) min f t (w) O( Tf ) w W where f = min w W T f t(w)
63 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Extensions Faster Rates [Srebro et al., 2010] f t (w t ) min f t (w) O( Tf ) w W where f = min w W T f t(w) Dynamic Regret [Zinkevich, 2003, Yang et al., 2016] R(u 1,...,u T ) = f t (w t ) f t (u t )
64 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Extensions Faster Rates [Srebro et al., 2010] f t (w t ) min f t (w) O( Tf ) w W where f = min w W T f t(w) Dynamic Regret [Zinkevich, 2003, Yang et al., 2016] R(u 1,...,u T ) = f t (w t ) f t (u t ) R(T,τ) = max [s,s+τ 1] [T] Adaptive Regret [Hazan and Seshadhri, 2007, Daniely et al., 2015] ( s+τ 1 t=s s+τ 1 f t (w t ) min w W t=s f t (w) )
65 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Reference I Cesa-bianchi, N., Conconi, A., and Gentile, C. (2002). On the generalization ability of on-line learning algorithms. In Advances in Neural Information Processing Systems 14, pages Cesa-Bianchi, N. and Lugosi, G. (2006). Prediction, Learning, and Games. Cambridge University Press. Daniely, A., Gonen, A., and Shalev-Shwartz, S. (2015). Strongly adaptive online learning. In Proceedings of The 32nd International Conference on Machine Learning. Hazan, E., Agarwal, A., and Kale, S. (2007). Logarithmic regret algorithms for online convex optimization. Machine Learning, 69(2-3): Hazan, E. and Seshadhri, C. (2007). Adaptive algorithms for online decision problems. Electronic Colloquium on Computational Complexity, 88. Kakade, S. M. and Tewari, A. (2009). On the generalization ability of online strongly convex programming algorithms. In Advances in Neural Information Processing Systems 21, pages
66 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Reference II Karp, R. M. (1992). On-line algorithms versus off-line algorithms: How much is it worth to know the future? In Proceedings of the IFIP 12th World Computer Congress on Algorithms, Software, Architecture Information Processing, pages Mahdavi, M., Zhang, L., and Jin, R. (2015). Lower and upper bounds on the generalization of stochastic exponentially concave optimization. In Proceedings of the 28th Conference on Learning Theory. Shalev-Shwartz, S. (2011). Online learning and online convex optimization. Foundations and Trends in Machine Learning, 4(2): Srebro, N., Sridharan, K., and Tewari, A. (2010). Optimistic rates for learning with a smooth loss. ArXiv e-prints, arxiv: Yang, T., Zhang, L., Jin, R., and Yi, J. (2016). Tracking slowly moving clairvoyant: Optimal dynamic regret of online learning with true and noisy gradient. In Proceedings of the 33rd International Conference on Machine Learning.
67 Introduction Expert Advice OCO Convex Functions Strongly Convex Functions Exponentially Co Reference III Zinkevich, M. (2003). Online convex programming and generalized infinitesimal gradient ascent. In Proceedings of the 20th International Conference on Machine Learning, pages
Adaptive Online Learning in Dynamic Environments
Adaptive Online Learning in Dynamic Environments Lijun Zhang, Shiyin Lu, Zhi-Hua Zhou National Key Laboratory for Novel Software Technology Nanjing University, Nanjing 210023, China {zhanglj, lusy, zhouzh}@lamda.nju.edu.cn
More informationStochastic Optimization
Introduction Related Work SGD Epoch-GD LM A DA NANJING UNIVERSITY Lijun Zhang Nanjing University, China May 26, 2017 Introduction Related Work SGD Epoch-GD Outline 1 Introduction 2 Related Work 3 Stochastic
More informationDynamic Regret of Strongly Adaptive Methods
Lijun Zhang 1 ianbao Yang 2 Rong Jin 3 Zhi-Hua Zhou 1 Abstract o cope with changing environments, recent developments in online learning have introduced the concepts of adaptive regret and dynamic regret
More informationOnline Learning and Online Convex Optimization
Online Learning and Online Convex Optimization Nicolò Cesa-Bianchi Università degli Studi di Milano N. Cesa-Bianchi (UNIMI) Online Learning 1 / 49 Summary 1 My beautiful regret 2 A supposedly fun game
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 Online Learning
More informationThe Online Approach to Machine Learning
The Online Approach to Machine Learning Nicolò Cesa-Bianchi Università degli Studi di Milano N. Cesa-Bianchi (UNIMI) Online Approach to ML 1 / 53 Summary 1 My beautiful regret 2 A supposedly fun game I
More informationOnline Optimization in Dynamic Environments: Improved Regret Rates for Strongly Convex Problems
216 IEEE 55th Conference on Decision and Control (CDC) ARIA Resort & Casino December 12-14, 216, Las Vegas, USA Online Optimization in Dynamic Environments: Improved Regret Rates for Strongly Convex Problems
More informationSupplementary Material of Dynamic Regret of Strongly Adaptive Methods
Supplementary Material of A Proof of Lemma 1 Lijun Zhang 1 ianbao Yang Rong Jin 3 Zhi-Hua Zhou 1 We first prove the first part of Lemma 1 Let k = log K t hen, integer t can be represented in the base-k
More informationAdaptive Online Gradient Descent
University of Pennsylvania ScholarlyCommons Statistics Papers Wharton Faculty Research 6-4-2007 Adaptive Online Gradient Descent Peter Bartlett Elad Hazan Alexander Rakhlin University of Pennsylvania Follow
More informationA Second-order Bound with Excess Losses
A Second-order Bound with Excess Losses Pierre Gaillard 12 Gilles Stoltz 2 Tim van Erven 3 1 EDF R&D, Clamart, France 2 GREGHEC: HEC Paris CNRS, Jouy-en-Josas, France 3 Leiden University, the Netherlands
More informationOLSO. Online Learning and Stochastic Optimization. Yoram Singer August 10, Google Research
OLSO Online Learning and Stochastic Optimization Yoram Singer August 10, 2016 Google Research References Introduction to Online Convex Optimization, Elad Hazan, Princeton University Online Learning and
More informationExponential Weights on the Hypercube in Polynomial Time
European Workshop on Reinforcement Learning 14 (2018) October 2018, Lille, France. Exponential Weights on the Hypercube in Polynomial Time College of Information and Computer Sciences University of Massachusetts
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 informationLower and Upper Bounds on the Generalization of Stochastic Exponentially Concave Optimization
JMLR: Workshop and Conference Proceedings vol 40:1 16, 2015 28th Annual Conference on Learning Theory Lower and Upper Bounds on the Generalization of Stochastic Exponentially Concave Optimization Mehrdad
More informationMinimizing Adaptive Regret with One Gradient per Iteration
Minimizing Adaptive Regret with One Gradient per Iteration Guanghui Wang, Dakuan Zhao, Lijun Zhang National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China wanggh@lamda.nju.edu.cn,
More informationFrom Bandits to Experts: A Tale of Domination and Independence
From Bandits to Experts: A Tale of Domination and Independence Nicolò Cesa-Bianchi Università degli Studi di Milano N. Cesa-Bianchi (UNIMI) Domination and Independence 1 / 1 From Bandits to Experts: A
More informationOn the Generalization Ability of Online Strongly Convex Programming Algorithms
On the Generalization Ability of Online Strongly Convex Programming Algorithms Sham M. Kakade I Chicago Chicago, IL 60637 sham@tti-c.org Ambuj ewari I Chicago Chicago, IL 60637 tewari@tti-c.org Abstract
More informationA survey: The convex optimization approach to regret minimization
A survey: The convex optimization approach to regret minimization Elad Hazan September 10, 2009 WORKING DRAFT Abstract A well studied and general setting for prediction and decision making is regret minimization
More informationAccelerating Online Convex Optimization via Adaptive Prediction
Mehryar Mohri Courant Institute and Google Research New York, NY 10012 mohri@cims.nyu.edu Scott Yang Courant Institute New York, NY 10012 yangs@cims.nyu.edu Abstract We present a powerful general framework
More informationNear-Optimal Algorithms for Online Matrix Prediction
JMLR: Workshop and Conference Proceedings vol 23 (2012) 38.1 38.13 25th Annual Conference on Learning Theory Near-Optimal Algorithms for Online Matrix Prediction Elad Hazan Technion - Israel Inst. of Tech.
More informationLecture 16: Perceptron and Exponential Weights Algorithm
EECS 598-005: Theoretical Foundations of Machine Learning Fall 2015 Lecture 16: Perceptron and Exponential Weights Algorithm Lecturer: Jacob Abernethy Scribes: Yue Wang, Editors: Weiqing Yu and Andrew
More informationThe Interplay Between Stability and Regret in Online Learning
The Interplay Between Stability and Regret in Online Learning Ankan Saha Department of Computer Science University of Chicago ankans@cs.uchicago.edu Prateek Jain Microsoft Research India prajain@microsoft.com
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 informationAdvanced Machine Learning
Advanced Machine Learning Online Convex Optimization MEHRYAR MOHRI MOHRI@ COURANT INSTITUTE & GOOGLE RESEARCH. Outline Online projected sub-gradient descent. Exponentiated Gradient (EG). Mirror descent.
More informationA Low Complexity Algorithm with O( T ) Regret and Finite Constraint Violations for Online Convex Optimization with Long Term Constraints
A Low Complexity Algorithm with O( T ) Regret and Finite Constraint Violations for Online Convex Optimization with Long Term Constraints Hao Yu and Michael J. Neely Department of Electrical Engineering
More informationSimultaneous Model Selection and Optimization through Parameter-free Stochastic Learning
Simultaneous Model Selection and Optimization through Parameter-free Stochastic Learning Francesco Orabona Yahoo! Labs New York, USA francesco@orabona.com Abstract Stochastic gradient descent algorithms
More informationAdaptivity and Optimism: An Improved Exponentiated Gradient Algorithm
Adaptivity and Optimism: An Improved Exponentiated Gradient Algorithm Jacob Steinhardt Percy Liang Stanford University {jsteinhardt,pliang}@cs.stanford.edu Jun 11, 2013 J. Steinhardt & P. Liang (Stanford)
More informationOptimal and Adaptive Online Learning
Optimal and Adaptive Online Learning Haipeng Luo Advisor: Robert Schapire Computer Science Department Princeton University Examples of Online Learning (a) Spam detection 2 / 34 Examples of Online Learning
More informationLearnability, Stability, Regularization and Strong Convexity
Learnability, Stability, Regularization and Strong Convexity Nati Srebro Shai Shalev-Shwartz HUJI Ohad Shamir Weizmann Karthik Sridharan Cornell Ambuj Tewari Michigan Toyota Technological Institute Chicago
More informationTutorial: PART 1. Online Convex Optimization, A Game- Theoretic Approach to Learning.
Tutorial: PART 1 Online Convex Optimization, A Game- Theoretic Approach to Learning http://www.cs.princeton.edu/~ehazan/tutorial/tutorial.htm Elad Hazan Princeton University Satyen Kale Yahoo Research
More informationOnline Convex Optimization
Advanced Course in Machine Learning Spring 2010 Online Convex Optimization Handouts are jointly prepared by Shie Mannor and Shai Shalev-Shwartz A convex repeated game is a two players game that is performed
More informationStochastic and Adversarial Online Learning without Hyperparameters
Stochastic and Adversarial Online Learning without Hyperparameters Ashok Cutkosky Department of Computer Science Stanford University ashokc@cs.stanford.edu Kwabena Boahen Department of Bioengineering Stanford
More informationOnline Learning with Experts & Multiplicative Weights Algorithms
Online Learning with Experts & Multiplicative Weights Algorithms CS 159 lecture #2 Stephan Zheng April 1, 2016 Caltech Table of contents 1. Online Learning with Experts With a perfect expert Without perfect
More informationTutorial: PART 2. Online Convex Optimization, A Game- Theoretic Approach to Learning
Tutorial: PART 2 Online Convex Optimization, A Game- Theoretic Approach to Learning Elad Hazan Princeton University Satyen Kale Yahoo Research Exploiting curvature: logarithmic regret Logarithmic regret
More informationNo-Regret Algorithms for Unconstrained Online Convex Optimization
No-Regret Algorithms for Unconstrained Online Convex Optimization Matthew Streeter Duolingo, Inc. Pittsburgh, PA 153 matt@duolingo.com H. Brendan McMahan Google, Inc. Seattle, WA 98103 mcmahan@google.com
More information1 Overview. 2 Learning from Experts. 2.1 Defining a meaningful benchmark. AM 221: Advanced Optimization Spring 2016
AM 1: Advanced Optimization Spring 016 Prof. Yaron Singer Lecture 11 March 3rd 1 Overview In this lecture we will introduce the notion of online convex optimization. This is an extremely useful framework
More informationOnline Optimization : Competing with Dynamic Comparators
Ali Jadbabaie Alexander Rakhlin Shahin Shahrampour Karthik Sridharan University of Pennsylvania University of Pennsylvania University of Pennsylvania Cornell University Abstract Recent literature on online
More informationOnline Learning: Random Averages, Combinatorial Parameters, and Learnability
Online Learning: Random Averages, Combinatorial Parameters, and Learnability Alexander Rakhlin Department of Statistics University of Pennsylvania Karthik Sridharan Toyota Technological Institute at Chicago
More informationBeyond the regret minimization barrier: an optimal algorithm for stochastic strongly-convex optimization
JMLR: Workshop and Conference Proceedings vol (2010) 1 16 24th Annual Conference on Learning heory Beyond the regret minimization barrier: an optimal algorithm for stochastic strongly-convex optimization
More informationOnline Optimization with Gradual Variations
JMLR: Workshop and Conference Proceedings vol (0) 0 Online Optimization with Gradual Variations Chao-Kai Chiang, Tianbao Yang 3 Chia-Jung Lee Mehrdad Mahdavi 3 Chi-Jen Lu Rong Jin 3 Shenghuo Zhu 4 Institute
More informationRegret bounded by gradual variation for online convex optimization
Noname manuscript No. will be inserted by the editor Regret bounded by gradual variation for online convex optimization Tianbao Yang Mehrdad Mahdavi Rong Jin Shenghuo Zhu Received: date / Accepted: date
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 informationSubgradient Methods for Maximum Margin Structured Learning
Nathan D. Ratliff ndr@ri.cmu.edu J. Andrew Bagnell dbagnell@ri.cmu.edu Robotics Institute, Carnegie Mellon University, Pittsburgh, PA. 15213 USA Martin A. Zinkevich maz@cs.ualberta.ca Department of Computing
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 informationOnline Convex Optimization. Gautam Goel, Milan Cvitkovic, and Ellen Feldman CS 159 4/5/2016
Online Convex Optimization Gautam Goel, Milan Cvitkovic, and Ellen Feldman CS 159 4/5/2016 The General Setting The General Setting (Cover) Given only the above, learning isn't always possible Some Natural
More informationFoundations of Machine Learning On-Line Learning. Mehryar Mohri Courant Institute and Google Research
Foundations of Machine Learning On-Line Learning Mehryar Mohri Courant Institute and Google Research mohri@cims.nyu.edu Motivation PAC learning: distribution fixed over time (training and test). IID assumption.
More informationGeneralization Bounds for Online Learning Algorithms with Pairwise Loss Functions
JMLR: Workshop and Conference Proceedings vol 3 0 3. 3. 5th Annual Conference on Learning Theory Generalization Bounds for Online Learning Algorithms with Pairwise Loss Functions Yuyang Wang Roni Khardon
More informationAdaptive Subgradient Methods for Online Learning and Stochastic Optimization John Duchi, Elad Hanzan, Yoram Singer
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization John Duchi, Elad Hanzan, Yoram Singer Vicente L. Malave February 23, 2011 Outline Notation minimize a number of functions φ
More informationOptimization, Learning, and Games with Predictable Sequences
Optimization, Learning, and Games with Predictable Sequences Alexander Rakhlin University of Pennsylvania Karthik Sridharan University of Pennsylvania Abstract We provide several applications of Optimistic
More informationExponentiated Gradient Descent
CSE599s, Spring 01, Online Learning Lecture 10-04/6/01 Lecturer: Ofer Dekel Exponentiated Gradient Descent Scribe: Albert Yu 1 Introduction In this lecture we review norms, dual norms, strong convexity,
More informationAlireza Shafaei. Machine Learning Reading Group The University of British Columbia Summer 2017
s s Machine Learning Reading Group The University of British Columbia Summer 2017 (OCO) Convex 1/29 Outline (OCO) Convex Stochastic Bernoulli s (OCO) Convex 2/29 At each iteration t, the player chooses
More informationLecture 23: Online convex optimization Online convex optimization: generalization of several algorithms
EECS 598-005: heoretical Foundations of Machine Learning Fall 2015 Lecture 23: Online convex optimization Lecturer: Jacob Abernethy Scribes: Vikas Dhiman Disclaimer: hese notes have not been subjected
More informationTHE WEIGHTED MAJORITY ALGORITHM
THE WEIGHTED MAJORITY ALGORITHM Csaba Szepesvári University of Alberta CMPUT 654 E-mail: szepesva@ualberta.ca UofA, October 3, 2006 OUTLINE 1 PREDICTION WITH EXPERT ADVICE 2 HALVING: FIND THE PERFECT EXPERT!
More informationNew bounds on the price of bandit feedback for mistake-bounded online multiclass learning
Journal of Machine Learning Research 1 8, 2017 Algorithmic Learning Theory 2017 New bounds on the price of bandit feedback for mistake-bounded online multiclass learning Philip M. Long Google, 1600 Amphitheatre
More informationDistributed online optimization over jointly connected digraphs
Distributed online optimization over jointly connected digraphs David Mateos-Núñez Jorge Cortés University of California, San Diego {dmateosn,cortes}@ucsd.edu Southern California Optimization Day UC San
More informationBandit Online Convex Optimization
March 31, 2015 Outline 1 OCO vs Bandit OCO 2 Gradient Estimates 3 Oblivious Adversary 4 Reshaping for Improved Rates 5 Adaptive Adversary 6 Concluding Remarks Review of (Online) Convex Optimization Set-up
More informationOnline Learning with Feedback Graphs
Online Learning with Feedback Graphs Nicolò Cesa-Bianchi Università degli Studi di Milano Joint work with: Noga Alon (Tel-Aviv University) Ofer Dekel (Microsoft Research) Tomer Koren (Technion and Microsoft
More informationStochastic Gradient Descent with Only One Projection
Stochastic Gradient Descent with Only One Projection Mehrdad Mahdavi, ianbao Yang, Rong Jin, Shenghuo Zhu, and Jinfeng Yi Dept. of Computer Science and Engineering, Michigan State University, MI, USA Machine
More informationApplications of on-line prediction. in telecommunication problems
Applications of on-line prediction in telecommunication problems Gábor Lugosi Pompeu Fabra University, Barcelona based on joint work with András György and Tamás Linder 1 Outline On-line prediction; Some
More informationAn Online Convex Optimization Approach to Blackwell s Approachability
Journal of Machine Learning Research 17 (2016) 1-23 Submitted 7/15; Revised 6/16; Published 8/16 An Online Convex Optimization Approach to Blackwell s Approachability Nahum Shimkin Faculty of Electrical
More informationDelay-Tolerant Online Convex Optimization: Unified Analysis and Adaptive-Gradient Algorithms
Delay-Tolerant Online Convex Optimization: Unified Analysis and Adaptive-Gradient Algorithms Pooria Joulani 1 András György 2 Csaba Szepesvári 1 1 Department of Computing Science, University of Alberta,
More information4.1 Online Convex Optimization
CS/CNS/EE 53: Advanced Topics in Machine Learning Topic: Online Convex Optimization and Online SVM Lecturer: Daniel Golovin Scribe: Xiaodi Hou Date: Jan 3, 4. Online Convex Optimization Definition 4..
More informationThe FTRL Algorithm with Strongly Convex Regularizers
CSE599s, Spring 202, Online Learning Lecture 8-04/9/202 The FTRL Algorithm with Strongly Convex Regularizers Lecturer: Brandan McMahan Scribe: Tamara Bonaci Introduction In the last lecture, we talked
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 informationA Drifting-Games Analysis for Online Learning and Applications to Boosting
A Drifting-Games Analysis for Online Learning and Applications to Boosting Haipeng Luo Department of Computer Science Princeton University Princeton, NJ 08540 haipengl@cs.princeton.edu Robert E. Schapire
More informationAgnostic Online learnability
Technical Report TTIC-TR-2008-2 October 2008 Agnostic Online learnability Shai Shalev-Shwartz Toyota Technological Institute Chicago shai@tti-c.org ABSTRACT We study a fundamental question. What classes
More informationarxiv: v1 [cs.lg] 23 Jan 2019
Cooperative Online Learning: Keeping your Neighbors Updated Nicolò Cesa-Bianchi, Tommaso R. Cesari, and Claire Monteleoni 2 Dipartimento di Informatica, Università degli Studi di Milano, Italy 2 Department
More informationLogarithmic Regret Algorithms for Online Convex Optimization
Logarithmic Regret Algorithms for Online Convex Optimization Elad Hazan 1, Adam Kalai 2, Satyen Kale 1, and Amit Agarwal 1 1 Princeton University {ehazan,satyen,aagarwal}@princeton.edu 2 TTI-Chicago kalai@tti-c.org
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 informationQuasi-Newton Algorithms for Non-smooth Online Strongly Convex Optimization. Mark Franklin Godwin
Quasi-Newton Algorithms for Non-smooth Online Strongly Convex Optimization by Mark Franklin Godwin A dissertation submitted in partial satisfaction of the requirements for the degree of Doctor of Philosophy
More informationExplore no more: Improved high-probability regret bounds for non-stochastic bandits
Explore no more: Improved high-probability regret bounds for non-stochastic bandits Gergely Neu SequeL team INRIA Lille Nord Europe gergely.neu@gmail.com Abstract This work addresses the problem of regret
More informationOnline and Stochastic Learning with a Human Cognitive Bias
Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence Online and Stochastic Learning with a Human Cognitive Bias Hidekazu Oiwa The University of Tokyo and JSPS Research Fellow 7-3-1
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}. 1. Prediction with expert advice. 2. With perfect
More informationLecture 16: FTRL and Online Mirror Descent
Lecture 6: FTRL and Online Mirror Descent Akshay Krishnamurthy akshay@cs.umass.edu November, 07 Recap Last time we saw two online learning algorithms. First we saw the Weighted Majority algorithm, which
More informationOnline Manifold Regularization: A New Learning Setting and Empirical Study
Online Manifold Regularization: A New Learning Setting and Empirical Study Andrew B. Goldberg 1, Ming Li 2, Xiaojin Zhu 1 1 Computer Sciences, University of Wisconsin Madison, USA. {goldberg,jerryzhu}@cs.wisc.edu
More informationCS261: A Second Course in Algorithms Lecture #11: Online Learning and the Multiplicative Weights Algorithm
CS61: A Second Course in Algorithms Lecture #11: Online Learning and the Multiplicative Weights Algorithm Tim Roughgarden February 9, 016 1 Online Algorithms This lecture begins the third module of the
More informationDistributed online optimization over jointly connected digraphs
Distributed online optimization over jointly connected digraphs David Mateos-Núñez Jorge Cortés University of California, San Diego {dmateosn,cortes}@ucsd.edu Mathematical Theory of Networks and Systems
More informationComputational and Statistical Learning Theory
Computational and Statistical Learning Theory TTIC 31120 Prof. Nati Srebro Lecture 17: Stochastic Optimization Part II: Realizable vs Agnostic Rates Part III: Nearest Neighbor Classification Stochastic
More informationTrade-Offs in Distributed Learning and Optimization
Trade-Offs in Distributed Learning and Optimization Ohad Shamir Weizmann Institute of Science Includes joint works with Yossi Arjevani, Nathan Srebro and Tong Zhang IHES Workshop March 2016 Distributed
More informationBandit Convex Optimization
March 7, 2017 Table of Contents 1 (BCO) 2 Projection Methods 3 Barrier Methods 4 Variance reduction 5 Other methods 6 Conclusion Learning scenario Compact convex action set K R d. For t = 1 to T : Predict
More informationLarge-scale Stochastic Optimization
Large-scale Stochastic Optimization 11-741/641/441 (Spring 2016) Hanxiao Liu hanxiaol@cs.cmu.edu March 24, 2016 1 / 22 Outline 1. Gradient Descent (GD) 2. Stochastic Gradient Descent (SGD) Formulation
More informationMaking Gradient Descent Optimal for Strongly Convex Stochastic Optimization
Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization Alexander Rakhlin University of Pennsylvania Ohad Shamir Microsoft Research New England Karthik Sridharan University of Pennsylvania
More informationOptimization for Machine Learning
Optimization for Machine Learning Editors: Suvrit Sra suvrit@gmail.com Max Planck Insitute for Biological Cybernetics 72076 Tübingen, Germany Sebastian Nowozin Microsoft Research Cambridge, CB3 0FB, United
More informationStochastic Gradient Descent
Stochastic Gradient Descent Machine Learning CSE546 Carlos Guestrin University of Washington October 9, 2013 1 Logistic Regression Logistic function (or Sigmoid): Learn P(Y X) directly Assume a particular
More informationThe convex optimization approach to regret minimization
The convex optimization approach to regret minimization Elad Hazan Technion - Israel Institute of Technology ehazan@ie.technion.ac.il Abstract A well studied and general setting for prediction and decision
More informationA simpler unified analysis of Budget Perceptrons
Ilya Sutskever University of Toronto, 6 King s College Rd., Toronto, Ontario, M5S 3G4, Canada ILYA@CS.UTORONTO.CA Abstract The kernel Perceptron is an appealing online learning algorithm that has a drawback:
More informationAccelerating Stochastic Optimization
Accelerating Stochastic Optimization Shai Shalev-Shwartz School of CS and Engineering, The Hebrew University of Jerusalem and Mobileye Master Class at Tel-Aviv, Tel-Aviv University, November 2014 Shalev-Shwartz
More informationClassification Logistic Regression
Announcements: Classification Logistic Regression Machine Learning CSE546 Sham Kakade University of Washington HW due on Friday. Today: Review: sub-gradients,lasso Logistic Regression October 3, 26 Sham
More informationarxiv: v4 [math.oc] 5 Jan 2016
Restarted SGD: Beating SGD without Smoothness and/or Strong Convexity arxiv:151.03107v4 [math.oc] 5 Jan 016 Tianbao Yang, Qihang Lin Department of Computer Science Department of Management Sciences The
More informationAdvanced Machine Learning
Advanced Machine Learning Follow-he-Perturbed Leader MEHRYAR MOHRI MOHRI@ COURAN INSIUE & GOOGLE RESEARCH. General Ideas Linear loss: decomposition as a sum along substructures. sum of edge losses in a
More informationRegret Bounds for Online Portfolio Selection with a Cardinality Constraint
Regret Bounds for Online Portfolio Selection with a Cardinality Constraint Shinji Ito NEC Corporation Daisuke Hatano RIKEN AIP Hanna Sumita okyo Metropolitan University Akihiro Yabe NEC Corporation akuro
More informationOnline Submodular Minimization
Online Submodular Minimization Elad Hazan IBM Almaden Research Center 650 Harry Rd, San Jose, CA 95120 hazan@us.ibm.com Satyen Kale Yahoo! Research 4301 Great America Parkway, Santa Clara, CA 95054 skale@yahoo-inc.com
More information0.1 Motivating example: weighted majority algorithm
princeton univ. F 16 cos 521: Advanced Algorithm Design Lecture 8: Decision-making under total uncertainty: the multiplicative weight algorithm Lecturer: Sanjeev Arora Scribe: Sanjeev Arora (Today s notes
More informationLinear Probability Forecasting
Linear Probability Forecasting Fedor Zhdanov and Yuri Kalnishkan Computer Learning Research Centre and Department of Computer Science, Royal Holloway, University of London, Egham, Surrey, TW0 0EX, UK {fedor,yura}@cs.rhul.ac.uk
More informationLecture 8: Decision-making under total uncertainty: the multiplicative weight algorithm. Lecturer: Sanjeev Arora
princeton univ. F 13 cos 521: Advanced Algorithm Design Lecture 8: Decision-making under total uncertainty: the multiplicative weight algorithm Lecturer: Sanjeev Arora Scribe: (Today s notes below are
More informationPrediction and Playing Games
Prediction and Playing Games Vineel Pratap vineel@eng.ucsd.edu February 20, 204 Chapter 7 : Prediction, Learning and Games - Cesa Binachi & Lugosi K-Person Normal Form Games Each player k (k =,..., K)
More informationRobust Selective Sampling from Single and Multiple Teachers
Robust Selective Sampling from Single and Multiple Teachers Ofer Dekel Microsoft Research oferd@microsoftcom Claudio Gentile DICOM, Università dell Insubria claudiogentile@uninsubriait Karthik Sridharan
More informationOnline Prediction Peter Bartlett
Online Prediction Peter Bartlett Statistics and EECS UC Berkeley and Mathematical Sciences Queensland University of Technology Online Prediction Repeated game: Cumulative loss: ˆL n = Decision method plays
More informationLinear Classification. CSE 6363 Machine Learning Vassilis Athitsos Computer Science and Engineering Department University of Texas at Arlington
Linear Classification CSE 6363 Machine Learning Vassilis Athitsos Computer Science and Engineering Department University of Texas at Arlington 1 Example of Linear Classification Red points: patterns belonging
More informationOnline Learning with Feedback Graphs
Online Learning with Feedback Graphs Claudio Gentile INRIA and Google NY clagentile@gmailcom NYC March 6th, 2018 1 Content of this lecture Regret analysis of sequential prediction problems lying between
More information