Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Regularizations of Inverse Problems
Search
Samuel Vaiter
September 06, 2013
Science
0
43
Regularizations of Inverse Problems
GRETSI'13, Quartz, Brest, September 2013.
Samuel Vaiter
September 06, 2013
Tweet
Share
More Decks by Samuel Vaiter
See All by Samuel Vaiter
Low Complexity Regularizations: A ''Localization'' Result
svaiter
0
65
A First Look at Proximal Methods
svaiter
0
210
Fast Distributed Total Variation
svaiter
0
110
Low Complexity Regularizations: A Localization Result
svaiter
0
67
Low Complexity Regularizations: a Localization Result
svaiter
0
120
Model Selection with Partly Smooth Functions
svaiter
0
41
Low Complexity Models: Robustness
svaiter
0
64
Low Complexity Models: Robustness and Sensivity
svaiter
0
36
Recovery Guarantees for Low Complexity Models
svaiter
1
76
Other Decks in Science
See All in Science
Quelles valorisations des logiciels vers le monde socio-économique dans un contexte de Science Ouverte ?
bluehats
1
550
機械学習 - K-means & 階層的クラスタリング
trycycle
PRO
0
1.1k
データから見る勝敗の法則 / The principle of victory discovered by science (open lecture in NSSU)
konakalab
1
180
Hakonwa-Quaternion
hiranabe
1
140
LayerXにおける業務の完全自動運転化に向けたAI技術活用事例 / layerx-ai-jsai2025
shimacos
2
15k
機械学習 - DBSCAN
trycycle
PRO
0
1.1k
データベース14: B+木 & ハッシュ索引
trycycle
PRO
0
500
統計的因果探索: 背景知識とデータにより因果仮説を探索する
sshimizu2006
4
1.1k
「美は世界を救う」を心理学で実証したい~クラファンを通じた新しい研究方法
jimpe_hitsuwari
1
170
システム数理と応用分野の未来を切り拓くロードマップ・エンターテインメント(スポーツ)への応用 / Applied mathematics for sports entertainment
konakalab
1
410
データベース10: 拡張実体関連モデル
trycycle
PRO
0
1k
データベース04: SQL (1/3) 単純質問 & 集約演算
trycycle
PRO
0
1k
Featured
See All Featured
Reflections from 52 weeks, 52 projects
jeffersonlam
353
21k
Keith and Marios Guide to Fast Websites
keithpitt
411
23k
Bash Introduction
62gerente
615
210k
Designing for Performance
lara
610
69k
Docker and Python
trallard
46
3.6k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
234
17k
Why You Should Never Use an ORM
jnunemaker
PRO
59
9.6k
Typedesign – Prime Four
hannesfritz
42
2.8k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
10
880
It's Worth the Effort
3n
187
28k
BBQ
matthewcrist
89
9.9k
The Cult of Friendly URLs
andyhume
79
6.6k
Transcript
Régularisation de problèmes inverses Analyse unifiée de la robustesse Samuel
VAITER CNRS, CEREMADE, Université Paris-Dauphine, France Travaux en collaboration avec M. GOLBABAEE, G. PEYRÉ et J. FADILI
Linear Inverse Problems inpainting denoising super-resolution Forward model y =
x0 + w observations noise input operator
The Variational Approach x argmin x RN 1 2 ||y
x||2 2 + J(x) Data fidelity Regularity
The Variational Approach x argmin x RN 1 2 ||y
x||2 2 + J(x) Data fidelity Regularity J(x) = || x||2 J(x) = || x||1
The Variational Approach x argmin x RN 1 2 ||y
x||2 2 + J(x) Data fidelity Regularity J(x) = || x||2 J(x) = || x||1 sparsity analysis-sparsity group-sparsity nuclear norm Tikhonov Total Variation Anti-sparse Polyhedral L1 + TV ... atomic norm decomposable norm Candidate J
Objectives Model selection performance x0 x w Prior model J
Objectives Model selection performance x0 x w Prior model J
Objectives Model selection performance x0 x w Prior model J
How close ? in term of SNR in term of features
Union of Linear Models Union of models: T T linear
spaces
Union of Linear Models Union of models: T T linear
spaces T sparsity
Union of Linear Models Union of models: T T linear
spaces block sparsity T sparsity
Union of Linear Models Union of models: T T linear
spaces block sparsity T sparsity analysis sparsity
Union of Linear Models Union of models: T T linear
spaces block sparsity low rank T sparsity analysis sparsity
Union of Linear Models Union of models: T T linear
spaces block sparsity low rank Objective Encode T in a function T sparsity analysis sparsity
Gauges 1 J(x) J : RN R+ convex J( x)
= J(x), 0
Gauges 1 J(x) J : RN R+ convex C C
= {x : J(x) 1} J( x) = J(x), 0
Gauges 1 J(x) J : RN R+ convex C C
= {x : J(x) 1} Geometry of C Union of Models (T )T T x T x x 0 T0 x x 0 T0 x 0 x T T0 ||x||1 |x1|+||x2,3|| ||x|| ||x|| J( x) = J(x), 0
Subdifferential |x| 0
Subdifferential |x| 0
J(x) = RN : x , J(x ) J(x)+ ,
x x Subdifferential |x| 0
J(x) = RN : x , J(x ) J(x)+ ,
x x Subdifferential |x| 0 |·|(0) = [ 1,1] x = 0, |·|(x) = {sign(x)}
From the Subdifferential to the Model J(x) x 0 J(x)
x 0
From the Subdifferential to the Model J(x) x 0 J(x)
x 0 Tx= VectHull( J(x)) Tx Tx Tx = : supp( ) supp(x)
From the Subdifferential to the Model J(x) x 0 J(x)
x 0 ex = ProjTx ( J(x)) ex ex ex = sign(x) Tx= VectHull( J(x)) Tx Tx Tx = : supp( ) supp(x)
Regularizations and their Models J(x) = ||x||1 ex = sign(x)
Tx = : supp( ) supp(x) x x J(x) = b ||xb|| ex = (N (xb))b B Tx = : supp( ) supp(x) x N (xb) = xb/||xb|| J(x) = ||x||∗ ex =UV Tx = : U V = 0 x x =UΛV ∗ J(x) = ||x||∞ ex = |I| 1 sign(x) Tx = : I sign(xI ) x x I = {i : |xi | = ||x||∞}
Dual Certificates and Model Selection x argmin x RN 1
2 ||y x||2 2 + J(x) Hypothesis: Ker Tx0 = {0} J regular enough
Dual Certificates and Model Selection x argmin x RN 1
2 ||y x||2 2 + J(x) Hypothesis: Ker Tx0 = {0} J regular enough ¯ D = Im ri( J(x0)) Tight dual certificates: x = x0 J(x) x
Dual Certificates and Model Selection x argmin x RN 1
2 ||y x||2 2 + J(x) Hypothesis: 0 = ( + Tx0 ) ex0 Minimal norm pre-certificate: Tx = Tx0 and ||x x0|| = O(||w||) If 0 ¯ D,||w|| small enough and ||w||, then x is the unique solution. Moreover, [V. et al. 2013] 1: [Fuchs 2004] 1 2: [Bach 2008] Ker Tx0 = {0} J regular enough ¯ D = Im ri( J(x0)) Tight dual certificates: x = x0 J(x) x
Example: Sparse Deconvolution x = i xi (· i) J(x)
= ||x||1 Increasing : reduces correlation. reduces resolution. x0 x0
Example: Sparse Deconvolution x = i xi (· i) J(x)
= ||x||1 Increasing : reduces correlation. reduces resolution. x0 x0 I = j : x0[j] = 0 || 0,Ic || < 1 0 ¯ D support recovery || 0,Ic || 1 2 20
Example: 1D TV Denoising J(x) = || x||1 = Id
I = {i : ( x0)i = 0} x0
Example: 1D TV Denoising J(x) = || x||1 = Id
I = {i : ( x0)i = 0} x0 +1 1 0 = div( 0) where j I,( 0)j = 0 x0 I J || 0,Ic || < 1 Support stability
Example: 1D TV Denoising J(x) = || x||1 = Id
I = {i : ( x0)i = 0} x0 +1 1 0 = div( 0) where j I,( 0)j = 0 x0 I J || 0,Ic || < 1 Support stability x0 || 0,Ic || = 1 2-stability only
Conclusion Gauges: encode linear models as singular points
Conclusion Gauges: encode linear models as singular points Certificates: guarantees
of model selection / 2 robustness (see poster 208 for a pure robustness result)
Conclusion Merci de votre attention ! Gauges: encode linear models
as singular points Certificates: guarantees of model selection / 2 robustness (see poster 208 for a pure robustness result)