ipiano inertial proximal algorithm for non convex
play

iPiano: Inertial Proximal Algorithm for Non-Convex Optimization - PowerPoint PPT Presentation

iPiano: Inertial Proximal Algorithm for Non-Convex Optimization David Stutz June 2, 2016 David Stutz | June 2, 2016 David Stutz | June 2, 2016 0/34 1/34 Table of Contents 1 Problem Related Work 2 Algorithm 3 Convergence 4


  1. iPiano: Inertial Proximal Algorithm for Non-Convex Optimization David Stutz June 2, 2016 David Stutz | June 2, 2016 David Stutz | June 2, 2016 0/34 1/34

  2. Table of Contents 1 Problem Related Work 2 Algorithm 3 Convergence 4 Implementation 5 6 Applications Conclusion 7 David Stutz | June 2, 2016 2/34

  3. Problem Problem. Minimize composite function x ∈ R d h ( x ) = min min n ∈ R d ( f ( x ) + g ( x )) (1) where – f : R d → R ∈ C 1 with L -Lipschitz continuous gradient; – g : dom ( g ) ⊂ R d → R ∞ is proper closed convex and lower semicontinuous; – and h coercive and bounded below by −∞ < h min := inf x ∈ R d h ( x ) . Ochs et al. [OCBP14] combine forward-backward splitting with an inertial force/momentum term to solve Equation (1) iteratively. David Stutz | June 2, 2016 3/34

  4. Problem Problem. Minimize composite function x ∈ R d h ( x ) = min min n ∈ R d ( f ( x ) + g ( x )) (1) where – f : R d → R ∈ C 1 with L -Lipschitz continuous gradient; – g : dom ( g ) ⊂ R d → R ∞ is proper closed convex and lower semicontinuous; – and h coercive and bounded below by −∞ < h min := inf x ∈ R d h ( x ) . Ochs et al. [OCBP14] combine forward-backward splitting with an inertial force/momentum term to solve Equation (1) iteratively. David Stutz | June 2, 2016 3/34

  5. Problem Problem. Minimize composite function x ∈ R d h ( x ) = min min n ∈ R d ( f ( x ) + g ( x )) (1) where – f : R d → R ∈ C 1 with L -Lipschitz continuous gradient; – g : dom ( g ) ⊂ R d → R ∞ is proper closed convex and lower semicontinuous; – and h coercive and bounded below by −∞ < h min := inf x ∈ R d h ( x ) . Ochs et al. [OCBP14] combine forward-backward splitting with an inertial force/momentum term to solve Equation (1) iteratively. David Stutz | June 2, 2016 3/34

  6. Problem Problem. Minimize composite function x ∈ R d h ( x ) = min min n ∈ R d ( f ( x ) + g ( x )) (1) where – f : R d → R ∈ C 1 with L -Lipschitz continuous gradient; – g : dom ( g ) ⊂ R d → R ∞ is proper closed convex and lower semicontinuous; – and h coercive and bounded below by −∞ < h min := inf x ∈ R d h ( x ) . Ochs et al. [OCBP14] combine forward-backward splitting with an inertial force/momentum term to solve Equation (1) iteratively. David Stutz | June 2, 2016 3/34

  7. Problem Problem. Minimize composite function x ∈ R d h ( x ) = min min n ∈ R d ( f ( x ) + g ( x )) (1) where – f : R d → R ∈ C 1 with L -Lipschitz continuous gradient; – g : dom ( g ) ⊂ R d → R ∞ is proper closed convex and lower semicontinuous; – and h coercive and bounded below by −∞ < h min := inf x ∈ R d h ( x ) . Ochs et al. [OCBP14] combine forward-backward splitting with an inertial force/momentum term to solve Equation (1) iteratively. David Stutz | June 2, 2016 3/34

  8. Table of Contents 1 Problem Related Work 2 Algorithm 3 Convergence 4 Implementation 5 6 Applications Conclusion 7 David Stutz | June 2, 2016 4/34

  9. Related Work Gradient descent for h ∈ C 1 : x ( n +1) = x ( n ) − α n ∇ h ( x ( n ) ) . Gradient descent with inertial force/momentum term: x ( n +1) = x ( n ) − α n ∇ h ( x ( n ) ) + β n ( x ( n ) − x ( n − 1) ) . Proximal point for h being proper closed convex: x ( n +1) = prox α n h ( x ( n ) ) . Forward-backward splitting for h = f + g with f ∈ C 1 and f , g being proper closed convex: x ( n +1) = prox α n g ( x ( n ) − α n ∇ f ( x ( n ) )) . David Stutz | June 2, 2016 5/34

  10. Related Work Gradient descent for h ∈ C 1 : x ( n +1) = x ( n ) − α n ∇ h ( x ( n ) ) . Gradient descent with inertial force/momentum term: x ( n +1) = x ( n ) − α n ∇ h ( x ( n ) ) + β n ( x ( n ) − x ( n − 1) ) . Proximal point for h being proper closed convex: x ( n +1) = prox α n h ( x ( n ) ) . Forward-backward splitting for h = f + g with f ∈ C 1 and f , g being proper closed convex: x ( n +1) = prox α n g ( x ( n ) − α n ∇ f ( x ( n ) )) . David Stutz | June 2, 2016 5/34

  11. Related Work Gradient descent for h ∈ C 1 : x ( n +1) = x ( n ) − α n ∇ h ( x ( n ) ) . Gradient descent with inertial force/momentum term: x ( n +1) = x ( n ) − α n ∇ h ( x ( n ) ) + β n ( x ( n ) − x ( n − 1) ) . Proximal point for h being proper closed convex: x ( n +1) = prox α n h ( x ( n ) ) . Forward-backward splitting for h = f + g with f ∈ C 1 and f , g being proper closed convex: x ( n +1) = prox α n g ( x ( n ) − α n ∇ f ( x ( n ) )) . David Stutz | June 2, 2016 5/34

  12. Related Work Gradient descent for h ∈ C 1 : x ( n +1) = x ( n ) − α n ∇ h ( x ( n ) ) . Gradient descent with inertial force/momentum term: x ( n +1) = x ( n ) − α n ∇ h ( x ( n ) ) + β n ( x ( n ) − x ( n − 1) ) . Proximal point for h being proper closed convex: x ( n +1) = prox α n h ( x ( n ) ) . Forward-backward splitting for h = f + g with f ∈ C 1 and f , g being proper closed convex: x ( n +1) = prox α n g ( x ( n ) − α n ∇ f ( x ( n ) )) . David Stutz | June 2, 2016 5/34

  13. Related Work Gradient descent for h ∈ C 1 : x ( n +1) = x ( n ) − α n ∇ h ( x ( n ) ) . Gradient descent with inertial force/momentum term: x ( n +1) = x ( n ) − α n ∇ h ( x ( n ) ) + β n ( x ( n ) − x ( n − 1) ) . Proximal point for h being proper closed convex: x ( n +1) = prox α n h ( x ( n ) ) . Forward-backward splitting for h = f + g with f ∈ C 1 and f , g being proper closed convex: x ( n +1) = prox α n g ( x ( n ) − α n ∇ f ( x ( n ) )) . David Stutz | June 2, 2016 5/34

  14. Table of Contents 1 Problem Related Work 2 Algorithm 3 Convergence 4 Implementation 5 6 Applications Conclusion 7 David Stutz | June 2, 2016 6/34

  15. Algorithm – Iterates and Backtracking Ochs et al. [OCBP14] combine forward-backward splitting with an inertial force/momentum term. x ( n +1) = prox α n g ( x ( n ) − α n ∇ f ( x ( n ) ) + β n ( x ( n ) − x ( n − 1) )) (2) with step size parameters ( α n ) n ∈ N and momentum parameters ( β n ) n ∈ N . Backtracking to estimate the local Lipschitz constant L n such that f ( x ( n +1) ) ≤ f ( x ( n ) )+ ∇ f ( x ( n ) ) T ( x ( n +1) − x ( n ) ) (3) + L n 2 � x ( n +1) − x ( n ) � 2 2 David Stutz | June 2, 2016 7/34

  16. Algorithm – Iterates and Backtracking Ochs et al. [OCBP14] combine forward-backward splitting with an inertial force/momentum term: x ( n +1) = prox α n g ( x ( n ) − α n ∇ f ( x ( n ) ) + β n ( x ( n ) − x ( n − 1) )) (2) with step size parameters ( α n ) n ∈ N and momentum parameters ( β n ) n ∈ N . Backtracking to estimate the local Lipschitz constant L n such that f ( x ( n +1) ) ≤ f ( x ( n ) )+ ∇ f ( x ( n ) ) T ( x ( n +1) − x ( n ) ) (3) + L n 2 � x ( n +1) − x ( n ) � 2 2 David Stutz | June 2, 2016 7/34

  17. Algorithm – Iterates and Backtracking Ochs et al. [OCBP14] combine forward-backward splitting with an inertial force/momentum term x ( n +1) = prox α n g ( x ( n ) − α n ∇ f ( x ( n ) ) + β n ( x ( n ) − x ( n − 1) )) (2) with step size parameters ( α n ) n ∈ N and momentum parameters ( β n ) n ∈ N . Backtracking to estimate the local Lipschitz constant L n such that f ( x ( n +1) ) ≤ f ( x ( n ) )+ ∇ f ( x ( n ) ) T ( x ( n +1) − x ( n ) ) (3) + L n 2 � x ( n +1) − x ( n ) � 2 2 David Stutz | June 2, 2016 7/34

  18. Algorithm – Iterates and Backtracking Ochs et al. [OCBP14] combine forward-backward splitting with an inertial force/momentum term x ( n +1) = prox α n g ( x ( n ) − α n ∇ f ( x ( n ) ) + β n ( x ( n ) − x ( n − 1) )) (2) with step size parameters ( α n ) n ∈ N and momentum parameters ( β n ) n ∈ N . Backtracking to estimate the local Lipschitz constant L n such that f ( x ( n +1) ) ≤ f ( x ( n ) )+ ∇ f ( x ( n ) ) T ( x ( n +1) − x ( n ) ) (3) + L n 2 � x ( n +1) − x ( n ) � 2 2 David Stutz | June 2, 2016 7/34

  19. Algorithm – iPiano Algorithm iPiano. 1: choose c 1 , c 2 > 0 close to zero, L − 1 > 0 , η > 1 , x (0) 2: x ( − 1) := x (0) 3: for n = 1 , . . . do 4: 5: 6: 7: choose α n ≥ c 1 , β n ≥ 0 8: 9: � � x ( n +1) = prox α n g x ( n ) − α n ∇ f ( x ( n ) ) + β n ( x ( n ) − x ( n − 1) ) 10: 11: 12: end for David Stutz | June 2, 2016 8/34

  20. Algorithm – iPiano Algorithm iPiano. 1: choose c 1 , c 2 > 0 close to zero, L − 1 > 0 , η > 1 , x (0) 2: x ( − 1) := x (0) 3: for n = 1 , . . . do 4: 5: 6: repeat 7: choose α n ≥ c 1 , β n ≥ 0 8: 2 − β n 2 − β n α n − L n 1 α n − L n 1 until δ n := 2 α n ≥ γ n := α n ≥ c 2 9: � � x ( n +1) = prox α n g x ( n ) − α n ∇ f ( x ( n ) ) + β n ( x ( n ) − x ( n − 1) ) 10: 11: 12: end for David Stutz | June 2, 2016 8/34

  21. Algorithm – iPiano Algorithm iPiano. 1: choose c 1 , c 2 > 0 close to zero, L − 1 > 0 , η > 1 , x (0) 2: x ( − 1) := x (0) 3: for n = 1 , . . . do L n := 1 η L n − 1 4: repeat 5: L n := ηL n 6: repeat 7: choose α n ≥ c 1 , β n ≥ 0 8: 2 − β n 2 − β n α n − L n 1 α n − L n 1 until δ n := 2 α n ≥ γ n := α n ≥ c 2 9: x ( n +1) = prox α n g � x ( n ) − α n ∇ f ( x ( n ) ) + β n ( x ( n ) − x ( n − 1) ) � 10: until (3) is satisifed for x ( n +1) 11: 12: end for David Stutz | June 2, 2016 8/34

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