derivative free methods for machine learning tasks
play

Derivative-Free Methods for Machine Learning Tasks Inverse Problem - PowerPoint PPT Presentation

EnKF Kovachki & Stuart Derivative-Free Methods for Machine Learning Tasks Inverse Problem Formulations The Ensemble Kalman Filter Ensemble Kalman Filter Numerics Nikola B. Kovachki 1 Andrew M. Stuart 1 1 Computational and Mathematical


  1. EnKF Kovachki & Stuart Derivative-Free Methods for Machine Learning Tasks Inverse Problem Formulations The Ensemble Kalman Filter Ensemble Kalman Filter Numerics Nikola B. Kovachki 1 Andrew M. Stuart 1 1 Computational and Mathematical Sciences California Institute of Technology Inverse Problems and Machine Learning February 9-11th, 2018

  2. Table of Contents EnKF Kovachki & Stuart Inverse Problem Formulations 1 Inverse Problem Formulations Ensemble Kalman Filter Numerics 2 Ensemble Kalman Filter 3 Numerics

  3. Table of Contents EnKF Kovachki & Stuart Inverse Problem Formulations 1 Inverse Problem Formulations Ensemble Kalman Filter Numerics 2 Ensemble Kalman Filter 3 Numerics

  4. Supervised Learning EnKF • Data : { ( x j , y j ) } N j =1 with x j ∈ X , y j ∈ Y and X , Y Hilbert spaces. Kovachki & • Find : G ( u |· ) : X → Y for parameter u ∈ U consistent with the data. Stuart • Concatenate : Inverse Problem Formulations y = G( u | x) + η Ensemble where G( ·| x) : U → Y N and η is model or data error. Kalman Filter Numerics • Losses : Φ( u ; x , y) N 1 � 2 � y − G( u | x) � 2 Y N + R ( u ) or − � y j , log G ( u | , x j ) � Y + R ( u ) j =1 • Standard Solution (SGD) : u = −∇ u Φ( u ; x , y); ˙ u (0) = u 0 u ∗ = u ( T )

  5. Example EnKF • Classification : Kovachki & Stuart Inverse Problem Formulations Ensemble Kalman Filter Numerics • NLP :

  6. Online Supervised Learning EnKF • Data : As before possibly with N = ∞ . Kovachki & • Dynamic : For j = 0 , 1 , 2 , . . . Stuart Inverse Problem u j +1 = u j Formulations Ensemble y j +1 = G ( u j +1 | x j +1 ) + η j +1 Kalman Filter Numerics • Find : u j given Y j = { y k } j k =1 and update sequentially. • Loss : Φ( u ; x , y ) 1 2 � y − G ( u | x ) � 2 Y + R ( u ) or − � y , log G ( u | x ) � Y + R ( u ) • Standard Solution (OGD) : u = −∇ u Φ( u ; x j +1 , y j +1 ); ˙ u (0) = u j u j +1 = u ( T j )

  7. Example EnKF • Model Improvement : Kovachki & Stuart Inverse Problem Formulations Ensemble Kalman Filter Numerics • Stream Data :

  8. Semi-Supervised Learning (on a graph) EnKF Kovachki & Bertozzi and Flenner 2012. (MMS) Stuart Bertozzi, Luo, Stuart, Zygalakis 2017. (preprint) Inverse Problem • Data : { x j } j ∈ Z and { y j } j ∈ Z ′ with Z ′ ⊂ Z and | Z ′ | ≪ | Z | . Formulations • Find : u : Z → R m such that Ensemble Kalman Filter Numerics ∀ j ∈ Z ′ y j = S ( u ( j )) + η j S : R m → Y is pre-specified. • Loss : 1 � � y j − S ( u ( j )) � 2 Φ( u ; x , y) = Y + R ( u ; x) 2 γ 2 j ∈ Z ′ • Standard Solution : Probit (convex optimization) or MCMC (Bayesian).

  9. Example EnKF Kovachki & Stuart • Clustering : Inverse Problem Formulations Ensemble Kalman Filter Numerics

  10. Table of Contents EnKF Kovachki & Stuart Inverse Problem Formulations 1 Inverse Problem Formulations Ensemble Kalman Filter Numerics 2 Ensemble Kalman Filter 3 Numerics

  11. Continous-time EnKF EnKF Kantas, Beskos, Jasra, (2014) (JUQ) Kovachki & Iglesias, Law and Stuart, 2013. (IP) Stuart • Inverse Problem : Inverse Problem η ∼ N (0 , Γ) y = G( u ) + η Formulations Ensemble u ∼ µ 0 ( u ) Kalman Filter Numerics • Sequential Monte Carlo (SMC) : µ n ( du ) ∝ exp( − nh Φ( u ; y )) µ 0 ( du ) • Approximate SMC (EnKF) : u ( j ) n +1 = u ( j ) n + C uw ( u n )( C ww ( u n ) + Γ) − 1 (y − G( u ( j ) n )) • Continous-time : Γ �→ 1 h Γ, h → 0 J u ( j ) = − 1 � � G( u ( k ) ) − ¯ G , G( u ( j ) ) − y � Γ u ( k ) ˙ J k =1

  12. Approximate Natural Gradient Decent EnKF Amari, 1998. (NC) Kovachki & Stuart • Linear : G( · ) = A · u ( j ) = − C ( u ) ∇ u Φ( u ( j ) , y) ˙ Inverse Problem Formulations where Ensemble Kalman Filter J Numerics C ( u ) = 1 Φ( u , y) = 1 ( u ( j ) − ¯ u ) ⊗ ( u ( j ) − ¯ � 2 � y − Au � 2 u ); Γ J j =1 • Natural Gradient Decent : u = − F − 1 ( u ) ∇ u Φ( u , y) ˙ • Cram´ er-Rao : u ] � F − 1 ( u ) Cov[ˆ

  13. Long-time Linear Behavior EnKF Schillings and Stuart 2017. (SINUM) Kovachki & Stuart Theorem Inverse Problem Suppse G( · ) = A · and that y is the image of a truth u † under A. Define Formulations r ( j ) ( t ) = u ( j ) ( t ) − u † then (under some assumptions) Ensemble Kalman Filter Numerics Ar ( j ) ( t ) = Ar ( j ) � ( t ) + Ar ( j ) ⊥ ( t ) with Ar ( j ) u (0)) } and Ar ( j ) ∈ span { A ( u ( j ) (0) − ¯ ⊥ ∈ span { A ( u ( j ) (0) − ¯ u (0)) } ⊥ . � Furthermore Ar ( j ) � ( t ) → 0 as t → ∞ Ar ( j ) ⊥ ( t ) = Ar (1) ⊥ (0) ∀ t ≥ 0 .

  14. Arbitrary Loss EnKF • Non-linear : Kovachki & u ( j ) = − C uw ( u )Γ − 1 (G( u ( j ) ) − y ) Stuart ˙ = − C uw ( u ) ∇ z Ψ(G( u ( j ) ) , y) Inverse Problem Formulations J Ensemble = − 1 � � G( u ( k ) ) − ¯ Kalman Filter G , ∇ z Ψ(G( u ( j ) ) , y) � u ( k ) J Numerics k =1 J C uw ( u ) = 1 Ψ(z , y) = 1 ( u ( j ) − ¯ � u ) ⊗ (G( u ( j ) ) − ¯ 2 � y − z � 2 G); Γ J j =1 • Concatenate : u = [ u (1) , . . . , u ( J ) ] u = − D ( u ) u ˙ where D ( jk ) ( u ) = 1 J � G( u ( k ) ) − ¯ G , ∇ z Ψ(G( u ( j ) ) , y) �

  15. Nesterov Momentum EnKF Kovachki & Su, Boyd, Cand´ es 2014. (NIPS) Stuart • Momentum : Inverse Problem Formulations   u + 3 u n +1 = v n − h ∇ f ( v n ) ¨ t ˙ u + ∇ f ( u ) = 0 Ensemble     Kalman Filter n ⇐ ⇒ v n +1 = u n +1 + n +3 ( u n +1 − u n ) u (0) = 0 ˙ Numerics   v 0 = u 0 u (0) = u 0   • Modified Limit : u ( j ) + 3 u ( j ) = − C uw ( u ) ∇ z Ψ(G( u ( j ) ) , y)  ¨ t ˙   u ( j ) (0) = 0 ˙ u ( j ) (0) = u ( j )   0

  16. Discrete Scheme EnKF Kovachki & • Concatenate : u = [ u (1) , . . . , u ( J ) ] Stuart Inverse Problem u + 3 Formulations ¨ t ˙ u = − D ( u ) u Ensemble Kalman Filter where Numerics D ( jk ) ( u ) = 1 J � G( u ( k ) ) − ¯ G , ∇ z Ψ(G( u ( j ) ) , y) � • Discretize :  u n +1 = v n − h n D ( v n ) v n   n n +3 ( u n +1 − u n ) v n +1 = u n +1 + v 0 = u 0 = [ u (1) 0 , . . . , u ( J )  0 ] T 

  17. Initialization, Noise, and Predictions EnKF • Initial Ensemble : Kovachki & u (1) 0 , . . . , u ( J ) ∼ µ 0 ( u ) Stuart 0 Inverse Problem • Noise (Supervised) : Formulations Ensemble v ( j ) n +1 = v ( j ) + ξ ( j ) ξ ( j ) Kalman Filter ˜ n +1 ∼ µ n +1 ( u ) n n +1 Numerics � Cov[ µ n +1 ] ∝ h n Cov[ µ 0 ] • Ensemble Refresh (Online) : u ( j ) u n + ξ ( j ) ξ ( j ) n +1 = ¯ n +1 ∼ µ 0 ( u ) n +1 • Predict : J u n +1 = 1 u ( j ) � ¯ n +1 J j =1

  18. Complete Algorithm EnKF Kovachki & Stuart • Mini-batch data (at each step): Inverse Problem l } m l } m Formulations x n = { x i ( n ) y n = { y i ( n ) l =1 l =1 Ensemble Kalman Filter where { i ( n ) 1 , . . . , i ( n ) Numerics m } ⊆ { 1 , . . . , N } . • Compute : use discrete scheme as shown with x �→ x n y �→ y n • Step-size : adaptive h h n = ǫ + � D n �

  19. Table of Contents EnKF Kovachki & Stuart Inverse Problem Formulations 1 Inverse Problem Formulations Ensemble Kalman Filter Numerics 2 Ensemble Kalman Filter 3 Numerics

  20. Convolutional Models EnKF Ba, Kiros and Hinton 2016. (NIPS) Kovachki & Stuart Net 1 ∼ 14k Net 2 ∼ 30k Conv12x3x3 Conv12x3x3 Inverse Problem Formulations MaxPool2x2 Conv12x3x3 Ensemble MaxPool2x2 Kalman Filter Conv24x3x3 Conv24x3x3 Numerics MaxPool2x2 Conv24x3x3 MaxPool2x2 Conv32x3x3 Conv32x3x3 MaxPool2x2 Conv32x3x3 FC-100 FC-100 FC-10 FC-10 • ReLU applied after each block. • Layer Normalization applied after each convolutional layer.

  21. MNIST Dataset EnKF LeCun and Cortes 1999. Kovachki & Stuart Inverse Problem Formulations Ensemble Kalman Filter Numerics

  22. MNIST Supervised EnKF Kovachki & Stuart Inverse Problem Formulations Ensemble Kalman Filter Numerics Figure: Test Accuracy of Net 1 on MNIST (batched). J Loss Momentum Noise Refresh 5000 Cross Entropy � � χ

  23. MNIST Online EnKF Kovachki & Stuart Inverse Problem Formulations Ensemble Kalman Filter Numerics Figure: Test Accuracy of Net 1 on MNIST (online). J Loss Momentum Noise Refresh 5000 Cross Entropy χ χ �

  24. Fashion MNIST Dataset EnKF Xiao, Rasul and Vollgraf 2017. Kovachki & Stuart Inverse Problem Formulations Ensemble Kalman Filter Numerics

  25. Fashion MNIST Supervised EnKF Kovachki & Stuart Inverse Problem Formulations Ensemble Kalman Filter Numerics Figure: Test Accuracy of Net 2 on Fashion MNIST (batched). J Loss Momentum Noise Refresh 5000 Cross Entropy � � χ

  26. RNN EnKF Kovachki & Stuart Inverse Problem Formulations Ensemble Kalman Filter Numerics

  27. Time Series Online EnKF Kovachki & Stuart Inverse Problem Formulations Ensemble Kalman Filter Numerics Figure: Time Series prediction with a RNN. J Loss Momentum Noise Refresh 1000 MSE χ χ χ

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend