Less is More: Computational Regularization by Subsampling
|
|
- Alban McLaughlin
- 5 years ago
- Views:
Transcription
1 Less is More: Computational Regularization by Subsampling Lorenzo Rosasco University of Genova - Istituto Italiano di Tecnologia Massachusetts Institute of Technology lcsl.mit.edu joint work with Alessandro Rudi, Raffaello Camoriano Jan 13th, 2016 UCL, London
2 A Starting Point Classically: Statistics and optimization distinct steps in algorithm design
3 A Starting Point Classically: Statistics and optimization distinct steps in algorithm design Large Scale: Consider interplay between statistics and optimization! (Bottou, Bousquet 08)
4 A Starting Point Classically: Statistics and optimization distinct steps in algorithm design Large Scale: Consider interplay between statistics and optimization! (Bottou, Bousquet 08) Computational Regularization: Computation tricks =regularization
5 Problem: Estimate f Supervised Learning f
6 Supervised Learning Problem: Estimate f given S n = {(x 1, y 1 ),..., (x n, y n )} f (x 1,y 1 ) (x 2,y 2) (x 3,y 3) (x 4,y 4) (x 5,y 5)
7 Supervised Learning Problem: Estimate f given S n = {(x 1, y 1 ),..., (x n, y n )} f (x 1,y 1 ) (x 2,y 2) (x 3,y 3) (x 4,y 4) (x 5,y 5) The Setting y i = f (x i ) + ε i i {1,..., n} ε i R, x i R d random (with unknown distribution) f unknown
8 Outline Learning with dictionaries and kernels Data Dependent Subsampling Data Independent Subsampling
9 Non-linear/non-parametric learning f(x) = M c i q(x, w i ) i=1
10 Non-linear/non-parametric learning f(x) = M c i q(x, w i ) i=1 q non linear function
11 Non-linear/non-parametric learning f(x) = M c i q(x, w i ) i=1 q non linear function w i R d centers
12 Non-linear/non-parametric learning f(x) = M c i q(x, w i ) i=1 q non linear function w i R d centers c i R coefficients
13 Non-linear/non-parametric learning f(x) = M c i q(x, w i ) i=1 q non linear function w i R d centers c i R coefficients M = M n could/should grow with n
14 Non-linear/non-parametric learning f(x) = M c i q(x, w i ) i=1 q non linear function w i R d centers c i R coefficients M = M n could/should grow with n Question: How to choose w i, c i and M given S n?
15 Learning with Positive Definite Kernels There is an elegant answer if: q is symmetric all the matrices Q ij = q(x i, x j ) are positive semi-definite 1 1 They have non-negative eigenvalues
16 Learning with Positive Definite Kernels There is an elegant answer if: q is symmetric all the matrices Q ij = q(x i, x j ) are positive semi-definite 1 Representer Theorem (Kimeldorf, Wahba 70; Schölkopf et al. 01) M = n, w i = x i, c i by convex optimization! 1 They have non-negative eigenvalues
17 Kernel Ridge Regression (KRR) a.k.a. Penalized Least Squares f λ = argmin f H 1 n n (y i f(x i )) 2 + λ f 2 i=1
18 Kernel Ridge Regression (KRR) a.k.a. Penalized Least Squares where f λ = argmin f H 1 n n (y i f(x i )) 2 + λ f 2 i=1 H = {f f(x) = M c i q(x, w i ), c i R, w i R }{{ d, }} M {{ N } } any center! any length! i=1
19 Kernel Ridge Regression (KRR) a.k.a. Penalized Least Squares where f λ = argmin f H 1 n n (y i f(x i )) 2 + λ f 2 i=1 H = {f f(x) = M c i q(x, w i ), c i R, w i R }{{ d, }} M {{ N } } any center! any length! i=1 Solution n f λ = c i q(x, x i ) with c = ( Q + λni) 1 ŷ i=1
20 KRR: Statistics
21 KRR: Statistics Well understood statistical properties: Classical Theorem If f H, then λ = 1 n E ( f λ (x) f (x)) 2 1 n
22 KRR: Statistics Well understood statistical properties: Classical Theorem If f H, then λ = 1 n E ( f λ (x) f (x)) 2 1 n Remarks
23 KRR: Statistics Well understood statistical properties: Classical Theorem If f H, then λ = 1 n E ( f λ (x) f (x)) 2 1 n Remarks 1. Optimal nonparametric bound
24 KRR: Statistics Well understood statistical properties: Classical Theorem If f H, then λ = 1 n E ( f λ (x) f (x)) 2 1 n Remarks 1. Optimal nonparametric bound 2. Results for general kernels (e.g. splines/sobolev etc.) λ = n 1 2s+1, E ( f λ (x) f (x)) 2 n 2s 2s+1
25 KRR: Statistics Well understood statistical properties: Classical Theorem If f H, then λ = 1 n E ( f λ (x) f (x)) 2 1 n Remarks 1. Optimal nonparametric bound 2. Results for general kernels (e.g. splines/sobolev etc.) λ = n 1 2s+1, E ( f λ (x) f (x)) 2 n 2s 2s+1 3. Adaptive tuning via cross validation 4. Proofs: analysis/linear algebra+ random matrices (Smale and Zhou + Caponnetto, De Vito, R.+ Steinwart)
26 KRR: Optimization n f λ = c i q(x, x i ) with c = ( Q + λni) 1 ŷ i=1 Linear System Complexity Space O(n 2 ) bq c = Time O(n 3 ) by
27 KRR: Optimization n f λ = c i q(x, x i ) with c = ( Q + λni) 1 ŷ i=1 Linear System Complexity Space O(n 2 ) bq c = Time O(n 3 ) by BIG DATA? Running out of time and space... Can this be fixed?
28 Beyond Tikhonov: Spectral Filtering ( ˆQ + λi) 1 approximation of ˆQ controlled by λ
29 Beyond Tikhonov: Spectral Filtering ( ˆQ + λi) 1 approximation of ˆQ controlled by λ Can we approximate ˆQ by saving computations?
30 Beyond Tikhonov: Spectral Filtering ( ˆQ + λi) 1 approximation of ˆQ controlled by λ Can we approximate ˆQ by saving computations? Yes!
31 Beyond Tikhonov: Spectral Filtering ( ˆQ + λi) 1 approximation of ˆQ controlled by λ Can we approximate ˆQ by saving computations? Yes! Spectral filtering (Engl 96- inverse problems, Rosasco et al. 05- ML ) g λ ( ˆQ) ˆQ The filter function g λ defines the form of the approximation
32 Spectral filtering Examples Tikhonov- ridge regression Truncated SVD principal component regression Landweber iteration GD/ L 2 -boosting nu-method accelerated GD/Chebyshev method...
33 Spectral filtering Examples Tikhonov- ridge regression Truncated SVD principal component regression Landweber iteration GD/ L 2 -boosting nu-method accelerated GD/Chebyshev method... Landweber iteration (truncated power series)... c t = g t ( ˆQ) t 1 = γ (I γ ˆQ) r ŷ r=0
34 Spectral filtering Examples Tikhonov- ridge regression Truncated SVD principal component regression Landweber iteration GD/ L 2 -boosting nu-method accelerated GD/Chebyshev method... Landweber iteration (truncated power series)... c t = g t ( ˆQ) t 1 = γ (I γ ˆQ) r ŷ r=0... it s GD for ERM!! r = 1... t c r = c r 1 γ( ˆQc r 1 ŷ), c 0 = 0
35 Semiconvergence 0.24 Empirical Error Expected Error Error Iteration
36 Early Stopping at Work 1.5 Fitting on the training set Iteration #
37 Early Stopping at Work 1.5 Fitting on the training set Iteration #
38 Early Stopping at Work 1.5 Fitting on the training set Iteration #
39 Early Stopping at Work 1.5 Fitting on the training set Iteration #
40 Statistics and computations with spectral filtering The different filters achieve essentially the same optimal statistical error!
41 Statistics and computations with spectral filtering The different filters achieve essentially the same optimal statistical error! Difference is in computations Filter Time Space Tikhonov n 3 n 2 GD n 2 λ 1 n 2 Accelerated GD n 2 λ 1/2 n 2 Truncated SVD n 2 λ γ n 2
42 Computational Regularization Arises Computational regularization: iterations control statistics and time complexity
43 Computational Regularization Arises Computational regularization: iterations control statistics and time complexity Built-in regularization path
44 Computational Regularization Arises Computational regularization: iterations control statistics and time complexity Built-in regularization path Is there an advantage going for on-line learning?
45 Computational Regularization Arises Computational regularization: iterations control statistics and time complexity Built-in regularization path Is there an advantage going for on-line learning? Not much, maybe n 2 log n? (Bach Dieluevet 15 R. Villa 15)
46 Computational Regularization Arises Computational regularization: iterations control statistics and time complexity Built-in regularization path Is there an advantage going for on-line learning? Not much, maybe n 2 log n? (Bach Dieluevet 15 R. Villa 15) Computational regularization: principles to control statistics, time and space complexity
47 Outline Learning with dictionaries and kernels Data Dependent Subsampling Data Independent Subsampling
48 1. pick w i at random... Subsampling
49 Subsampling 1. pick w i at random... from training set (Smola, Scholköpf 00) w 1,..., w M x 1,... x n M n
50 Subsampling 1. pick w i at random... from training set (Smola, Scholköpf 00) w 1,..., w M x 1,... x n M n 2. perform KRR on H M = {f f(x) = M i=1 c i q(x, w i ), c i R, w i R d, M N}.
51 Subsampling 1. pick w i at random... from training set (Smola, Scholköpf 00) w 1,..., w M x 1,... x n M n 2. perform KRR on H M = {f f(x) = M i=1 c i q(x, w i ), c i R, w i R d, M N}. Linear System bq M c = by Complexity Space O(n 2 ) O(nM) Time O(n 3 ) O(nM 2 )
52 Subsampling 1. pick w i at random... from training set (Smola, Scholköpf 00) w 1,..., w M x 1,... x n M n 2. perform KRR on H M = {f f(x) = M i=1 c i q(x, w i ), c i R, w i R d, M N}. Linear System bq M c = by Complexity Space O(n 2 ) O(nM) Time O(n 3 ) O(nM 2 ) What about statistics? What s the price for efficient computations?
53 Putting our Result in Context *Many* different subsampling schemes (Smola, Scholkopf 00; Williams, Seeger 01; )
54 Putting our Result in Context *Many* different subsampling schemes (Smola, Scholkopf 00; Williams, Seeger 01; ) Theoretical guarantees mainly on matrix approximation (Mahoney and Drineas 09; Cortes et al 10, Kumar et al ) Q Q M 1 M
55 Putting our Result in Context *Many* different subsampling schemes (Smola, Scholkopf 00; Williams, Seeger 01; ) Theoretical guarantees mainly on matrix approximation (Mahoney and Drineas 09; Cortes et al 10, Kumar et al ) Q Q M 1 M Few prediction guarantees either suboptimal or in restricted setting (Cortes et al. 10; Jin et al. 11, Bach 13, Alaoui, Mahoney 14)
56 Main Result (Rudi, Camoriano, Rosasco, 15) Theorem If f H, then λ = 1 n, M = 1 λ, E ( f λ,m (x) f (x)) 2 1 n
57 Main Result (Rudi, Camoriano, Rosasco, 15) Theorem If f H, then λ = 1 n, M = 1 λ, E ( f λ,m (x) f (x)) 2 1 n Remarks
58 Main Result (Rudi, Camoriano, Rosasco, 15) Theorem If f H, then λ = 1 n, M = 1 λ, E ( f λ,m (x) f (x)) 2 1 n Remarks 1. Subsampling achives optimal bound...
59 Main Result (Rudi, Camoriano, Rosasco, 15) Theorem If f H, then λ = 1 n, M = 1 λ, E ( f λ,m (x) f (x)) 2 1 n Remarks 1. Subsampling achives optimal bound with M n!!
60 Main Result (Rudi, Camoriano, Rosasco, 15) Theorem If f H, then λ = 1 n, M = 1 λ, E ( f λ,m (x) f (x)) 2 1 n Remarks 1. Subsampling achives optimal bound with M n!! 3. More generally, λ = n 1 2s+1, M = 1 λ, E x ( f λ,m (x) f (x)) 2 n 2s 2s+1
61 Main Result (Rudi, Camoriano, Rosasco, 15) Theorem If f H, then λ = 1 n, M = 1 λ, E ( f λ,m (x) f (x)) 2 1 n Remarks 1. Subsampling achives optimal bound with M n!! 3. More generally, λ = n 1 2s+1, M = 1 λ, E x ( f λ,m (x) f (x)) 2 n 2s 2s+1 Note: An interesting insight is obtained rewriting the result...
62 Computational Regularization by Subsampling (Rudi, Camoriano, Rosasco, 15) A simple idea: swap the role of λ and M...
63 Computational Regularization by Subsampling (Rudi, Camoriano, Rosasco, 15) A simple idea: swap the role of λ and M... Theorem If f H, then M = n 1 2s+1, λ = 1 M, E x ( f λ,m (x) f (x)) 2 n 2s 2s+1
64 Computational Regularization by Subsampling (Rudi, Camoriano, Rosasco, 15) A simple idea: swap the role of λ and M... Theorem If f H, then M = n 1 2s+1, λ = 1 M, E x ( f λ,m (x) f (x)) 2 n 2s 2s+1 λ and M play the same role new interpretation: subsampling regularizes!
65 Computational Regularization by Subsampling (Rudi, Camoriano, Rosasco, 15) A simple idea: swap the role of λ and M... Theorem If f H, then M = n 1 2s+1, λ = 1 M, E x ( f λ,m (x) f (x)) 2 n 2s 2s+1 λ and M play the same role new interpretation: subsampling regularizes! New natural incremental algorithm... Algorithm
66 Computational Regularization by Subsampling (Rudi, Camoriano, Rosasco, 15) A simple idea: swap the role of λ and M... Theorem If f H, then M = n 1 2s+1, λ = 1 M, E x ( f λ,m (x) f (x)) 2 n 2s 2s+1 λ and M play the same role new interpretation: subsampling regularizes! New natural incremental algorithm... Algorithm 1. Pick a center + compute solution
67 Computational Regularization by Subsampling (Rudi, Camoriano, Rosasco, 15) A simple idea: swap the role of λ and M... Theorem If f H, then M = n 1 2s+1, λ = 1 M, E x ( f λ,m (x) f (x)) 2 n 2s 2s+1 λ and M play the same role new interpretation: subsampling regularizes! New natural incremental algorithm... Algorithm 1. Pick a center + compute solution 2. Pick another center + rank one update
68 Computational Regularization by Subsampling (Rudi, Camoriano, Rosasco, 15) A simple idea: swap the role of λ and M... Theorem If f H, then M = n 1 2s+1, λ = 1 M, E x ( f λ,m (x) f (x)) 2 n 2s 2s+1 λ and M play the same role new interpretation: subsampling regularizes! New natural incremental algorithm... Algorithm 1. Pick a center + compute solution 2. Pick another center + rank one update 3. Pick another center...
69 CoRe Illustrated n, λ are fixed Validation Error Computation controls stability! Time/space requirement tailored to generalization
70 Experiments comparable/better w.r.t. the state of the art Dataset n tr d Incremental Standard Standard Random Fastfood CoRe KRLS Nyström Features RF Ins. Co ± CPU ± CT slices ± NA Year Pred ± NA Forest ± NA Random Features (Rahimi, Recht 07) Fastfood (Le et al. 13)
71 Summary so far Optimal learning with data dependent subsampling Computational regularization: subsampling regularizes!
72 Summary so far Optimal learning with data dependent subsampling Computational regularization: subsampling regularizes! Few more questions: Can one do better than uniform sampling? What about data independent sampling?
73 (Approximate) Leverage scores Leverage scores l i (t) = ( Q( Q + tni) 1 ) ii
74 (Approximate) Leverage scores Leverage scores l i (t) = ( Q( Q + tni) 1 ) ii ALS With probability at least 1 δ, 1 T l i(t) l i (t) T l i (t)
75 (Approximate) Leverage scores Leverage scores l i (t) = ( Q( Q + tni) 1 ) ii ALS With probability at least 1 δ, 1 T l i(t) l i (t) T l i (t) ALS subsampling Pick w 1,..., w M x 1,... x n with replacement, and probability P t (i) = l i (t)/ j lj (t).
76 Learning with ALS Subsampling (Rudi, Camoriano, Rosasco, 15) Theorem If f H and the integral operator associated to q has eigenvalue decay i 1 γ, γ (0, 1) then λ = n 1 1+γ, M = 1 λ γ, E ( f λ,m (x) f (x)) 2 n 1 1+γ
77 Learning with ALS Subsampling (Rudi, Camoriano, Rosasco, 15) Theorem If f H and the integral operator associated to q has eigenvalue decay i 1 γ, γ (0, 1) then λ = n 1 1+γ, M = 1 λ γ, E ( f λ,m (x) f (x)) 2 n 1 1+γ Non uniform subsampling achieves optimal bound
78 Learning with ALS Subsampling (Rudi, Camoriano, Rosasco, 15) Theorem If f H and the integral operator associated to q has eigenvalue decay i 1 γ, γ (0, 1) then λ = n 1 1+γ, M = 1 λ γ, E ( f λ,m (x) f (x)) 2 n 1 1+γ Non uniform subsampling achieves optimal bound Most importantly: potentially much fewer samples needed
79 Learning with ALS Subsampling (Rudi, Camoriano, Rosasco, 15) Theorem If f H and the integral operator associated to q has eigenvalue decay i 1 γ, γ (0, 1) then λ = n 1 1+γ, M = 1 λ γ, E ( f λ,m (x) f (x)) 2 n 1 1+γ Non uniform subsampling achieves optimal bound Most importantly: potentially much fewer samples needed Need efficient ALS computation (... )
80 Learning with ALS Subsampling (Rudi, Camoriano, Rosasco, 15) Theorem If f H and the integral operator associated to q has eigenvalue decay i 1 γ, γ (0, 1) then λ = n 1 1+γ, M = 1 λ γ, E ( f λ,m (x) f (x)) 2 n 1 1+γ Non uniform subsampling achieves optimal bound Most importantly: potentially much fewer samples needed Need efficient ALS computation (... ) Extensions to more general sampling schemes are possible
81 Outline Learning with dictionaries and kernels Data Dependent Subsampling Data Independent Subsampling
82 Random Features
83 Random Features f(x) = M c i q(x, w i ) i=1 q general non linear function
84 Random Features f(x) = M c i q(x, w i ) i=1 q general non linear function pick w i at random according to a distribution µ w 1,..., w M µ
85 Random Features f(x) = M c i q(x, w i ) i=1 q general non linear function pick w i at random according to a distribution µ w 1,..., w M µ perform KRR on M H M = {f f(x) = c i q(x, w i ), c i R}. i=1
86 Random Fourier Features (Rahimi, Recht 07) Consider q(x, w) = e iwt x,
87 Random Fourier Features (Rahimi, Recht 07) Consider q(x, w) = e iwt x, w µ(w) = N (0, I)
88 Random Fourier Features (Rahimi, Recht 07) Consider q(x, w) = e iwt x, w µ(w) = N (0, I) Then E w [q(x, w)q(x, w)] = e x x 2γ = K(x, x )
89 Random Fourier Features (Rahimi, Recht 07) Consider q(x, w) = e iwt x, w µ(w) = N (0, I) Then E w [q(x, w)q(x, w)] = e x x 2γ = K(x, x ) By sampling w 1,..., w M we are considering the approximating kernel 1 M M [q(x, w i )q(x, w i )] = K(x, x ) i=1
90 More Random Features translation invariant kernels K(x, x ) = H(x x ),
91 More Random Features translation invariant kernels K(x, x ) = H(x x ), q(x, w) = e iwt x,
92 More Random Features translation invariant kernels K(x, x ) = H(x x ), q(x, w) = e iwt x, w µ = F(H)
93 More Random Features translation invariant kernels K(x, x ) = H(x x ), q(x, w) = e iwt x, w µ = F(H) infinite neural nets kernels
94 More Random Features translation invariant kernels K(x, x ) = H(x x ), q(x, w) = e iwt x, w µ = F(H) infinite neural nets kernels q(x, w) = w T x + b +,
95 More Random Features translation invariant kernels K(x, x ) = H(x x ), q(x, w) = e iwt x, w µ = F(H) infinite neural nets kernels q(x, w) = w T x + b +, (w, b) µ = U[S d ]
96 More Random Features translation invariant kernels K(x, x ) = H(x x ), q(x, w) = e iwt x, w µ = F(H) infinite neural nets kernels q(x, w) = w T x + b +, (w, b) µ = U[S d ] infinite dot product kernels homogeneous additive kernels group invariant kernels... Note: Connections with hashing and sketching techniques.
97 Properties of Random Features
98 Properties of Random Features Optimization Time: O(n 3 ) O(nM 2 ) Space: O(n 2 ) O(nM)
99 Properties of Random Features Optimization Time: O(n 3 ) O(nM 2 ) Space: O(n 2 ) O(nM) Statistics As before: do we pay a price for efficient computations?
100 Previous works
101 Previous works *Many* different random features for different kernels (Rahimi, Recht 07, Vedaldi, Zisserman, )
102 Previous works *Many* different random features for different kernels (Rahimi, Recht 07, Vedaldi, Zisserman, ) Theoretical guarantees: mainly kernel approximation (Rahimi, Recht 07,..., Sriperumbudur and Szabo 15) K(x, x ) K(x, x ) 1 M
103 Previous works *Many* different random features for different kernels (Rahimi, Recht 07, Vedaldi, Zisserman, ) Theoretical guarantees: mainly kernel approximation (Rahimi, Recht 07,..., Sriperumbudur and Szabo 15) K(x, x ) K(x, x ) 1 M Statistical guarantees suboptimal or in restricted setting (Rahimi, Recht 09, Yang et al ,Bach 15 )
104 Main Result Let q(x, w) = e iwt x,
105 Main Result Let ( q(x, w) = e iwt x 1, w µ(w) = c d 1 + w 2 ) d+1 2
106 Main Result Let ( q(x, w) = e iwt x 1, w µ(w) = c d 1 + w 2 ) d+1 2 Theorem If f H s Sobolev space, then λ = n 1 2s+1, M = 1 λ 2s, E ( f λ,m (x) f (x)) 2 n 2s 2s+1
107 Main Result Let ( q(x, w) = e iwt x 1, w µ(w) = c d 1 + w 2 ) d+1 2 Theorem If f H s Sobolev space, then λ = n 1 2s+1, M = 1 λ 2s, E ( f λ,m (x) f (x)) 2 n 2s 2s+1 Random feature achieves optimal bound!
108 Main Result Let ( q(x, w) = e iwt x 1, w µ(w) = c d 1 + w 2 ) d+1 2 Theorem If f H s Sobolev space, then λ = n 1 2s+1, M = 1 λ 2s, E ( f λ,m (x) f (x)) 2 n 2s 2s+1 Random feature achieves optimal bound! Efficient worst case subsampling M n, but cannot exploit smoothness.
109 Remarks & Extensions Nÿstrom vs Random features Both achieve optimal rates Nÿstrom seems to need fewer samples (random centers)
110 Remarks & Extensions Nÿstrom vs Random features Both achieve optimal rates Nÿstrom seems to need fewer samples (random centers) How tight are the results?
111 Remarks & Extensions Nÿstrom vs Random features Both achieve optimal rates Nÿstrom seems to need fewer samples (random centers) How tight are the results? log λ Test Error log M test error
112 Contributions Optimal bounds for data dependent/independent subsampling Subsampling: Nÿstrom vs Random features Beyond ridge regression: early stopping and multiple passes SGD (coming up in AISTATS!)
113 Contributions Optimal bounds for data dependent/independent subsampling Subsampling: Nÿstrom vs Random features Beyond ridge regression: early stopping and multiple passes SGD (coming up in AISTATS!) Some questions: Quest for the best sampling Regularization by projection: inverse problems and preconditioning Beyond randomization: non convex optimization?
114 Contributions Optimal bounds for data dependent/independent subsampling Subsampling: Nÿstrom vs Random features Beyond ridge regression: early stopping and multiple passes SGD (coming up in AISTATS!) Some questions: Quest for the best sampling Regularization by projection: inverse problems and preconditioning Beyond randomization: non convex optimization? Some perspectives: Computational regularization: subsampling regularizes Algorithm design: Control stability with computations
Less is More: Computational Regularization by Subsampling
Less is More: Computational Regularization by Subsampling Lorenzo Rosasco University of Genova - Istituto Italiano di Tecnologia Massachusetts Institute of Technology lcsl.mit.edu joint work with Alessandro
More informationTUM 2016 Class 3 Large scale learning by regularization
TUM 2016 Class 3 Large scale learning by regularization Lorenzo Rosasco UNIGE-MIT-IIT July 25, 2016 Learning problem Solve min w E(w), E(w) = dρ(x, y)l(w x, y) given (x 1, y 1 ),..., (x n, y n ) Beyond
More informationOptimal kernel methods for large scale learning
Optimal kernel methods for large scale learning Alessandro Rudi INRIA - École Normale Supérieure, Paris joint work with Luigi Carratino, Lorenzo Rosasco 6 Mar 2018 École Polytechnique Learning problem
More informationStochastic optimization in Hilbert spaces
Stochastic optimization in Hilbert spaces Aymeric Dieuleveut Aymeric Dieuleveut Stochastic optimization Hilbert spaces 1 / 48 Outline Learning vs Statistics Aymeric Dieuleveut Stochastic optimization Hilbert
More informationOslo Class 4 Early Stopping and Spectral Regularization
RegML2017@SIMULA Oslo Class 4 Early Stopping and Spectral Regularization Lorenzo Rosasco UNIGE-MIT-IIT June 28, 2016 Learning problem Solve min w E(w), E(w) = dρ(x, y)l(w x, y) given (x 1, y 1 ),..., (x
More informationStatistical Optimality of Stochastic Gradient Descent through Multiple Passes
Statistical Optimality of Stochastic Gradient Descent through Multiple Passes Francis Bach INRIA - Ecole Normale Supérieure, Paris, France ÉCOLE NORMALE SUPÉRIEURE Joint work with Loucas Pillaud-Vivien
More informationApproximate Kernel PCA with Random Features
Approximate Kernel PCA with Random Features (Computational vs. Statistical Tradeoff) Bharath K. Sriperumbudur Department of Statistics, Pennsylvania State University Journées de Statistique Paris May 28,
More informationAn inverse problem perspective on machine learning
An inverse problem perspective on machine learning Lorenzo Rosasco University of Genova Massachusetts Institute of Technology Istituto Italiano di Tecnologia lcsl.mit.edu Feb 9th, 2018 Inverse Problems
More informationApproximate Kernel Methods
Lecture 3 Approximate Kernel Methods Bharath K. Sriperumbudur Department of Statistics, Pennsylvania State University Machine Learning Summer School Tübingen, 207 Outline Motivating example Ridge regression
More informationSpectral Regularization
Spectral Regularization Lorenzo Rosasco 9.520 Class 07 February 27, 2008 About this class Goal To discuss how a class of regularization methods originally designed for solving ill-posed inverse problems,
More informationRegularization via Spectral Filtering
Regularization via Spectral Filtering Lorenzo Rosasco MIT, 9.520 Class 7 About this class Goal To discuss how a class of regularization methods originally designed for solving ill-posed inverse problems,
More informationConvergence Rates of Kernel Quadrature Rules
Convergence Rates of Kernel Quadrature Rules Francis Bach INRIA - Ecole Normale Supérieure, Paris, France ÉCOLE NORMALE SUPÉRIEURE NIPS workshop on probabilistic integration - Dec. 2015 Outline Introduction
More informationRegML 2018 Class 2 Tikhonov regularization and kernels
RegML 2018 Class 2 Tikhonov regularization and kernels Lorenzo Rosasco UNIGE-MIT-IIT June 17, 2018 Learning problem Problem For H {f f : X Y }, solve min E(f), f H dρ(x, y)l(f(x), y) given S n = (x i,
More informationEarly Stopping for Computational Learning
Early Stopping for Computational Learning Lorenzo Rosasco Universita di Genova, Massachusetts Institute of Technology Istituto Italiano di Tecnologia CBMM Sestri Levante, September, 2014 joint work with
More informationBasis Expansion and Nonlinear SVM. Kai Yu
Basis Expansion and Nonlinear SVM Kai Yu Linear Classifiers f(x) =w > x + b z(x) = sign(f(x)) Help to learn more general cases, e.g., nonlinear models 8/7/12 2 Nonlinear Classifiers via Basis Expansion
More informationIterative Convex Regularization
Iterative Convex Regularization Lorenzo Rosasco Universita di Genova Universita di Genova Istituto Italiano di Tecnologia Massachusetts Institute of Technology Optimization and Statistical Learning Workshop,
More informationKernel Learning via Random Fourier Representations
Kernel Learning via Random Fourier Representations L. Law, M. Mider, X. Miscouridou, S. Ip, A. Wang Module 5: Machine Learning L. Law, M. Mider, X. Miscouridou, S. Ip, A. Wang Kernel Learning via Random
More informationMemory Efficient Kernel Approximation
Si Si Department of Computer Science University of Texas at Austin ICML Beijing, China June 23, 2014 Joint work with Cho-Jui Hsieh and Inderjit S. Dhillon Outline Background Motivation Low-Rank vs. Block
More informationMathematical Methods for Data Analysis
Mathematical Methods for Data Analysis Massimiliano Pontil Istituto Italiano di Tecnologia and Department of Computer Science University College London Massimiliano Pontil Mathematical Methods for Data
More information2 Tikhonov Regularization and ERM
Introduction Here we discusses how a class of regularization methods originally designed to solve ill-posed inverse problems give rise to regularized learning algorithms. These algorithms are kernel methods
More informationLearning sets and subspaces: a spectral approach
Learning sets and subspaces: a spectral approach Alessandro Rudi DIBRIS, Università di Genova Optimization and dynamical processes in Statistical learning and inverse problems Sept 8-12, 2014 A world of
More informationReproducing Kernel Hilbert Spaces
Reproducing Kernel Hilbert Spaces Lorenzo Rosasco 9.520 Class 03 February 9, 2011 About this class Goal To introduce a particularly useful family of hypothesis spaces called Reproducing Kernel Hilbert
More informationPack only the essentials: distributed sequential sampling for adaptive kernel DL
Pack only the essentials: distributed sequential sampling for adaptive kernel DL with Daniele Calandriello and Alessandro Lazaric SequeL team, Inria Lille - Nord Europe, France appeared in AISTATS 2017
More informationOptimal Convergence for Distributed Learning with Stochastic Gradient Methods and Spectral Algorithms
Optimal Convergence for Distributed Learning with Stochastic Gradient Methods and Spectral Algorithms Junhong Lin Volkan Cevher Laboratory for Information and Inference Systems École Polytechnique Fédérale
More informationOnline Gradient Descent Learning Algorithms
DISI, Genova, December 2006 Online Gradient Descent Learning Algorithms Yiming Ying (joint work with Massimiliano Pontil) Department of Computer Science, University College London Introduction Outline
More informationTowards Deep Kernel Machines
Towards Deep Kernel Machines Julien Mairal Inria, Grenoble Prague, April, 2017 Julien Mairal Towards deep kernel machines 1/51 Part I: Scientific Context Julien Mairal Towards deep kernel machines 2/51
More informationSVRG++ with Non-uniform Sampling
SVRG++ with Non-uniform Sampling Tamás Kern András György Department of Electrical and Electronic Engineering Imperial College London, London, UK, SW7 2BT {tamas.kern15,a.gyorgy}@imperial.ac.uk Abstract
More informationAnalysis of Nyström Method with Sequential Ridge Leverage Score Sampling
Analysis of Nyström Method with Sequential Ridge Leverage Score Sampling Daniele Calandriello SequeL team INRIA Lille - Nord Europe Alessandro Lazaric SequeL team INRIA Lille - Nord Europe Michal Valko
More informationOslo Class 2 Tikhonov regularization and kernels
RegML2017@SIMULA Oslo Class 2 Tikhonov regularization and kernels Lorenzo Rosasco UNIGE-MIT-IIT May 3, 2017 Learning problem Problem For H {f f : X Y }, solve min E(f), f H dρ(x, y)l(f(x), y) given S n
More informationReproducing Kernel Hilbert Spaces
Reproducing Kernel Hilbert Spaces Lorenzo Rosasco 9.520 Class 03 February 12, 2007 About this class Goal To introduce a particularly useful family of hypothesis spaces called Reproducing Kernel Hilbert
More informationDistributed Adaptive Sampling for Kernel Matrix Approximation
Daniele Calandriello Alessandro Lazaric Michal Valko SequeL team, INRIA Lille - Nord Europe Abstract Most kernel-based methods, such as kernel regression, kernel PCA, ICA, or k-means clustering, do not
More informationRegularization Algorithms for Learning
DISI, UNIGE Texas, 10/19/07 plan motivation setting elastic net regularization - iterative thresholding algorithms - error estimates and parameter choice applications motivations starting point of many
More informationOptimal Rates for Multi-pass Stochastic Gradient Methods
Journal of Machine Learning Research 8 (07) -47 Submitted 3/7; Revised 8/7; Published 0/7 Optimal Rates for Multi-pass Stochastic Gradient Methods Junhong Lin Laboratory for Computational and Statistical
More informationDiffeomorphic Warping. Ben Recht August 17, 2006 Joint work with Ali Rahimi (Intel)
Diffeomorphic Warping Ben Recht August 17, 2006 Joint work with Ali Rahimi (Intel) What Manifold Learning Isn t Common features of Manifold Learning Algorithms: 1-1 charting Dense sampling Geometric Assumptions
More informationECE521 lecture 4: 19 January Optimization, MLE, regularization
ECE521 lecture 4: 19 January 2017 Optimization, MLE, regularization First four lectures Lectures 1 and 2: Intro to ML Probability review Types of loss functions and algorithms Lecture 3: KNN Convexity
More informationSpectral Filtering for MultiOutput Learning
Spectral Filtering for MultiOutput Learning Lorenzo Rosasco Center for Biological and Computational Learning, MIT Universita di Genova, Italy Plan Learning with kernels Multioutput kernel and regularization
More informationReproducing Kernel Hilbert Spaces
9.520: Statistical Learning Theory and Applications February 10th, 2010 Reproducing Kernel Hilbert Spaces Lecturer: Lorenzo Rosasco Scribe: Greg Durrett 1 Introduction In the previous two lectures, we
More informationStochastic Gradient Descent. Ryan Tibshirani Convex Optimization
Stochastic Gradient Descent Ryan Tibshirani Convex Optimization 10-725 Last time: proximal gradient descent Consider the problem min x g(x) + h(x) with g, h convex, g differentiable, and h simple in so
More informationStatistically and Computationally Efficient Variance Estimator for Kernel Ridge Regression
Statistically and Computationally Efficient Variance Estimator for Kernel Ridge Regression Meimei Liu Department of Statistical Science Duke University Durham, IN - 27708 Email: meimei.liu@duke.edu Jean
More informationMLCC 2017 Regularization Networks I: Linear Models
MLCC 2017 Regularization Networks I: Linear Models Lorenzo Rosasco UNIGE-MIT-IIT June 27, 2017 About this class We introduce a class of learning algorithms based on Tikhonov regularization We study computational
More informationFALKON: An Optimal Large Scale Kernel Method
FALKON: An Optimal Large Scale Kernel Method Alessandro Rudi INRIA Sierra Project-team, École Normale Supérieure, Paris Luigi Carratino University of Genoa Genova, Italy Lorenzo Rosasco University of Genoa,
More informationStochastic Optimization Algorithms Beyond SG
Stochastic Optimization Algorithms Beyond SG Frank E. Curtis 1, Lehigh University involving joint work with Léon Bottou, Facebook AI Research Jorge Nocedal, Northwestern University Optimization Methods
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 informationApproximate Principal Components Analysis of Large Data Sets
Approximate Principal Components Analysis of Large Data Sets Daniel J. McDonald Department of Statistics Indiana University mypage.iu.edu/ dajmcdon April 27, 2016 Approximation-Regularization for Analysis
More informationsublinear time low-rank approximation of positive semidefinite matrices Cameron Musco (MIT) and David P. Woodru (CMU)
sublinear time low-rank approximation of positive semidefinite matrices Cameron Musco (MIT) and David P. Woodru (CMU) 0 overview Our Contributions: 1 overview Our Contributions: A near optimal low-rank
More informationDistribution Regression
Zoltán Szabó (École Polytechnique) Joint work with Bharath K. Sriperumbudur (Department of Statistics, PSU), Barnabás Póczos (ML Department, CMU), Arthur Gretton (Gatsby Unit, UCL) Dagstuhl Seminar 16481
More informationReproducing Kernel Hilbert Spaces
Reproducing Kernel Hilbert Spaces Lorenzo Rosasco 9.520 Class 03 February 11, 2009 About this class Goal To introduce a particularly useful family of hypothesis spaces called Reproducing Kernel Hilbert
More informationSemi-Nonparametric Inferences for Massive Data
Semi-Nonparametric Inferences for Massive Data Guang Cheng 1 Department of Statistics Purdue University Statistics Seminar at NCSU October, 2015 1 Acknowledge NSF, Simons Foundation and ONR. A Joint Work
More informationarxiv: v1 [cs.lg] 11 Jan 2012
arxiv:20.246v [cs.lg] Jan 202 Pierre Machart LIF, LSIS, CNRS, Aix-Marseille Université Thomas Peel LIF, LATP, CNRS, Aix-Marseille Université Sandrine Anthoine LATP, CNRS, Aix-Marseille Université Liva
More informationContents. 1 Introduction. 1.1 History of Optimization ALG-ML SEMINAR LISSA: LINEAR TIME SECOND-ORDER STOCHASTIC ALGORITHM FEBRUARY 23, 2016
ALG-ML SEMINAR LISSA: LINEAR TIME SECOND-ORDER STOCHASTIC ALGORITHM FEBRUARY 23, 2016 LECTURERS: NAMAN AGARWAL AND BRIAN BULLINS SCRIBE: KIRAN VODRAHALLI Contents 1 Introduction 1 1.1 History of Optimization.....................................
More informationDistribution Regression: A Simple Technique with Minimax-optimal Guarantee
Distribution Regression: A Simple Technique with Minimax-optimal Guarantee (CMAP, École Polytechnique) Joint work with Bharath K. Sriperumbudur (Department of Statistics, PSU), Barnabás Póczos (ML Department,
More informationApproximate Spectral Clustering via Randomized Sketching
Approximate Spectral Clustering via Randomized Sketching Christos Boutsidis Yahoo! Labs, New York Joint work with Alex Gittens (Ebay), Anju Kambadur (IBM) The big picture: sketch and solve Tradeoff: Speed
More informationSimple Optimization, Bigger Models, and Faster Learning. Niao He
Simple Optimization, Bigger Models, and Faster Learning Niao He Big Data Symposium, UIUC, 2016 Big Data, Big Picture Niao He (UIUC) 2/26 Big Data, Big Picture Niao He (UIUC) 3/26 Big Data, Big Picture
More informationClass 2 & 3 Overfitting & Regularization
Class 2 & 3 Overfitting & Regularization Carlo Ciliberto Department of Computer Science, UCL October 18, 2017 Last Class The goal of Statistical Learning Theory is to find a good estimator f n : X Y, approximating
More informationLearning with stochastic proximal gradient
Learning with stochastic proximal gradient Lorenzo Rosasco DIBRIS, Università di Genova Via Dodecaneso, 35 16146 Genova, Italy lrosasco@mit.edu Silvia Villa, Băng Công Vũ Laboratory for Computational and
More informationUnsupervised Learning Techniques Class 07, 1 March 2006 Andrea Caponnetto
Unsupervised Learning Techniques 9.520 Class 07, 1 March 2006 Andrea Caponnetto About this class Goal To introduce some methods for unsupervised learning: Gaussian Mixtures, K-Means, ISOMAP, HLLE, Laplacian
More informationDiscriminative Models
No.5 Discriminative Models Hui Jiang Department of Electrical Engineering and Computer Science Lassonde School of Engineering York University, Toronto, Canada Outline Generative vs. Discriminative models
More informationSpectral Algorithms for Supervised Learning
LETTER Communicated by David Hardoon Spectral Algorithms for Supervised Learning L. Lo Gerfo logerfo@disi.unige.it L. Rosasco rosasco@disi.unige.it F. Odone odone@disi.unige.it Dipartimento di Informatica
More informationMulti-Task Learning and Matrix Regularization
Multi-Task Learning and Matrix Regularization Andreas Argyriou Department of Computer Science University College London Collaborators T. Evgeniou (INSEAD) R. Hauser (University of Oxford) M. Herbster (University
More informationarxiv: v6 [stat.ml] 17 Mar 2016
Less is More: Nyström Computational Regularization Alessandro Rudi 1 Raffaello Camoriano 1,2 Lorenzo Rosasco 1,3 ale rudi@mit.edu raffaello.camoriano@iit.it lrosasco@mit.edu arxiv:1507.04717v6 [stat.ml]
More informationINTRODUCTION TO DATA SCIENCE
INTRODUCTION TO DATA SCIENCE JOHN P DICKERSON Lecture #13 3/9/2017 CMSC320 Tuesdays & Thursdays 3:30pm 4:45pm ANNOUNCEMENTS Mini-Project #1 is due Saturday night (3/11): Seems like people are able to do
More informationBig Data Analytics. Lucas Rego Drumond
Big Data Analytics Lucas Rego Drumond Information Systems and Machine Learning Lab (ISMLL) Institute of Computer Science University of Hildesheim, Germany Predictive Models Predictive Models 1 / 34 Outline
More informationOptimal Distributed Learning with Multi-pass Stochastic Gradient Methods
Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods Junhong Lin Volkan Cevher Abstract We study generalization properties of distributed algorithms in the setting of nonparametric
More informationAdvances in kernel exponential families
Advances in kernel exponential families Arthur Gretton Gatsby Computational Neuroscience Unit, University College London NIPS, 2017 1/39 Outline Motivating application: Fast estimation of complex multivariate
More informationComputational tractability of machine learning algorithms for tall fat data
Computational tractability of machine learning algorithms for tall fat data Getting good enough solutions as fast as possible Vikas Chandrakant Raykar vikas@cs.umd.edu University of Maryland, CollegePark
More informationBig Data Analytics: Optimization and Randomization
Big Data Analytics: Optimization and Randomization Tianbao Yang Tutorial@ACML 2015 Hong Kong Department of Computer Science, The University of Iowa, IA, USA Nov. 20, 2015 Yang Tutorial for ACML 15 Nov.
More informationDiscriminative Models
No.5 Discriminative Models Hui Jiang Department of Electrical Engineering and Computer Science Lassonde School of Engineering York University, Toronto, Canada Outline Generative vs. Discriminative models
More informationAn Adaptive Test of Independence with Analytic Kernel Embeddings
An Adaptive Test of Independence with Analytic Kernel Embeddings Wittawat Jitkrittum 1 Zoltán Szabó 2 Arthur Gretton 1 1 Gatsby Unit, University College London 2 CMAP, École Polytechnique ICML 2017, Sydney
More informationAlgorithmic Stability and Generalization Christoph Lampert
Algorithmic Stability and Generalization Christoph Lampert November 28, 2018 1 / 32 IST Austria (Institute of Science and Technology Austria) institute for basic research opened in 2009 located in outskirts
More informationSparse Approximation and Variable Selection
Sparse Approximation and Variable Selection Lorenzo Rosasco 9.520 Class 07 February 26, 2007 About this class Goal To introduce the problem of variable selection, discuss its connection to sparse approximation
More informationBeyond stochastic gradient descent for large-scale machine learning
Beyond stochastic gradient descent for large-scale machine learning Francis Bach INRIA - Ecole Normale Supérieure, Paris, France Joint work with Eric Moulines - October 2014 Big data revolution? A new
More informationKernel-based Approximation. Methods using MATLAB. Gregory Fasshauer. Interdisciplinary Mathematical Sciences. Michael McCourt.
SINGAPORE SHANGHAI Vol TAIPEI - Interdisciplinary Mathematical Sciences 19 Kernel-based Approximation Methods using MATLAB Gregory Fasshauer Illinois Institute of Technology, USA Michael McCourt University
More informationConvergence rates of spectral methods for statistical inverse learning problems
Convergence rates of spectral methods for statistical inverse learning problems G. Blanchard Universtität Potsdam UCL/Gatsby unit, 04/11/2015 Joint work with N. Mücke (U. Potsdam); N. Krämer (U. München)
More informationOptimization for Machine Learning
Optimization for Machine Learning (Lecture 3-A - Convex) SUVRIT SRA Massachusetts Institute of Technology Special thanks: Francis Bach (INRIA, ENS) (for sharing this material, and permitting its use) MPI-IS
More informationSupport Vector Machines: Training with Stochastic Gradient Descent. Machine Learning Fall 2017
Support Vector Machines: Training with Stochastic Gradient Descent Machine Learning Fall 2017 1 Support vector machines Training by maximizing margin The SVM objective Solving the SVM optimization problem
More informationNystrom Method for Approximating the GMM Kernel
Nystrom Method for Approximating the GMM Kernel Ping Li Department of Statistics and Biostatistics Department of omputer Science Rutgers University Piscataway, NJ 0, USA pingli@stat.rutgers.edu Abstract
More informationAn Improved Conjugate Gradient Scheme to the Solution of Least Squares SVM
An Improved Conjugate Gradient Scheme to the Solution of Least Squares SVM Wei Chu Chong Jin Ong chuwei@gatsby.ucl.ac.uk mpeongcj@nus.edu.sg S. Sathiya Keerthi mpessk@nus.edu.sg Control Division, Department
More informationLearning gradients: prescriptive models
Department of Statistical Science Institute for Genome Sciences & Policy Department of Computer Science Duke University May 11, 2007 Relevant papers Learning Coordinate Covariances via Gradients. Sayan
More informationRegularized Least Squares
Regularized Least Squares Ryan M. Rifkin Google, Inc. 2008 Basics: Data Data points S = {(X 1, Y 1 ),...,(X n, Y n )}. We let X simultaneously refer to the set {X 1,...,X n } and to the n by d matrix whose
More informationStochastic Variance Reduction for Nonconvex Optimization. Barnabás Póczos
1 Stochastic Variance Reduction for Nonconvex Optimization Barnabás Póczos Contents 2 Stochastic Variance Reduction for Nonconvex Optimization Joint work with Sashank Reddi, Ahmed Hefny, Suvrit Sra, and
More informationEmpirical Risk Minimization
Empirical Risk Minimization Fabrice Rossi SAMM Université Paris 1 Panthéon Sorbonne 2018 Outline Introduction PAC learning ERM in practice 2 General setting Data X the input space and Y the output space
More informationECE 5424: Introduction to Machine Learning
ECE 5424: Introduction to Machine Learning Topics: Ensemble Methods: Bagging, Boosting PAC Learning Readings: Murphy 16.4;; Hastie 16 Stefan Lee Virginia Tech Fighting the bias-variance tradeoff Simple
More informationSparse Random Features Algorithm as Coordinate Descent in Hilbert Space
Sparse Random Features Algorithm as Coordinate Descent in Hilbert Space Ian E.H. Yen 1 Ting-Wei Lin Shou-De Lin Pradeep Ravikumar 1 Inderjit S. Dhillon 1 Department of Computer Science 1: University of
More informationDistribution Regression with Minimax-Optimal Guarantee
Distribution Regression with Minimax-Optimal Guarantee (Gatsby Unit, UCL) Joint work with Bharath K. Sriperumbudur (Department of Statistics, PSU), Barnabás Póczos (ML Department, CMU), Arthur Gretton
More informationIntroductory Machine Learning Notes 1
Introductory Machine Learning Notes 1 Lorenzo Rosasco DIBRIS, Universita degli Studi di Genova LCSL, Massachusetts Institute of Technology and Istituto Italiano di Tecnologia lrosasco@mit.edu December
More informationCS540 Machine learning Lecture 5
CS540 Machine learning Lecture 5 1 Last time Basis functions for linear regression Normal equations QR SVD - briefly 2 This time Geometry of least squares (again) SVD more slowly LMS Ridge regression 3
More informationwhat can deep learning learn from linear regression? Benjamin Recht University of California, Berkeley
what can deep learning learn from linear regression? Benjamin Recht University of California, Berkeley Collaborators Joint work with Samy Bengio, Moritz Hardt, Michael Jordan, Jason Lee, Max Simchowitz,
More informationThe Kernel Trick, Gram Matrices, and Feature Extraction. CS6787 Lecture 4 Fall 2017
The Kernel Trick, Gram Matrices, and Feature Extraction CS6787 Lecture 4 Fall 2017 Momentum for Principle Component Analysis CS6787 Lecture 3.1 Fall 2017 Principle Component Analysis Setting: find the
More informationFunctional SVD for Big Data
Functional SVD for Big Data Pan Chao April 23, 2014 Pan Chao Functional SVD for Big Data April 23, 2014 1 / 24 Outline 1 One-Way Functional SVD a) Interpretation b) Robustness c) CV/GCV 2 Two-Way Problem
More informationECE 5984: Introduction to Machine Learning
ECE 5984: Introduction to Machine Learning Topics: Ensemble Methods: Bagging, Boosting Readings: Murphy 16.4; Hastie 16 Dhruv Batra Virginia Tech Administrativia HW3 Due: April 14, 11:55pm You will implement
More informationSCMA292 Mathematical Modeling : Machine Learning. Krikamol Muandet. Department of Mathematics Faculty of Science, Mahidol University.
SCMA292 Mathematical Modeling : Machine Learning Krikamol Muandet Department of Mathematics Faculty of Science, Mahidol University February 9, 2016 Outline Quick Recap of Least Square Ridge Regression
More informationLarge-scale Image Annotation by Efficient and Robust Kernel Metric Learning
Large-scale Image Annotation by Efficient and Robust Kernel Metric Learning Supplementary Material Zheyun Feng Rong Jin Anil Jain Department of Computer Science and Engineering, Michigan State University,
More informationThe Learning Problem and Regularization Class 03, 11 February 2004 Tomaso Poggio and Sayan Mukherjee
The Learning Problem and Regularization 9.520 Class 03, 11 February 2004 Tomaso Poggio and Sayan Mukherjee About this class Goal To introduce a particularly useful family of hypothesis spaces called Reproducing
More informationMIT 9.520/6.860, Fall 2017 Statistical Learning Theory and Applications. Class 19: Data Representation by Design
MIT 9.520/6.860, Fall 2017 Statistical Learning Theory and Applications Class 19: Data Representation by Design What is data representation? Let X be a data-space X M (M) F (M) X A data representation
More informationhttps://goo.gl/kfxweg KYOTO UNIVERSITY Statistical Machine Learning Theory Sparsity Hisashi Kashima kashima@i.kyoto-u.ac.jp DEPARTMENT OF INTELLIGENCE SCIENCE AND TECHNOLOGY 1 KYOTO UNIVERSITY Topics:
More informationOnline Kernel PCA with Entropic Matrix Updates
Dima Kuzmin Manfred K. Warmuth Computer Science Department, University of California - Santa Cruz dima@cse.ucsc.edu manfred@cse.ucsc.edu Abstract A number of updates for density matrices have been developed
More informationClassification. The goal: map from input X to a label Y. Y has a discrete set of possible values. We focused on binary Y (values 0 or 1).
Regression and PCA Classification The goal: map from input X to a label Y. Y has a discrete set of possible values We focused on binary Y (values 0 or 1). But we also discussed larger number of classes
More informationarxiv: v1 [stat.ml] 31 Oct 2018
On Fast Leverage Score Sampling and Optimal Learning Alessandro Rudi, alessandro.rudi@inria.fr Luigi Carratino 3 luigi.carratino@dibris.unige.it Daniele Calandriello,2 daniele.calandriello@iit.it Lorenzo
More informationSemi-Supervised Learning in Gigantic Image Collections. Rob Fergus (New York University) Yair Weiss (Hebrew University) Antonio Torralba (MIT)
Semi-Supervised Learning in Gigantic Image Collections Rob Fergus (New York University) Yair Weiss (Hebrew University) Antonio Torralba (MIT) Gigantic Image Collections What does the world look like? High
More informationDivide and Conquer Kernel Ridge Regression. A Distributed Algorithm with Minimax Optimal Rates
: A Distributed Algorithm with Minimax Optimal Rates Yuchen Zhang, John C. Duchi, Martin Wainwright (UC Berkeley;http://arxiv.org/pdf/1305.509; Apr 9, 014) Gatsby Unit, Tea Talk June 10, 014 Outline Motivation.
More information