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
42
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
59
A First Look at Proximal Methods
svaiter
0
210
Fast Distributed Total Variation
svaiter
0
110
Low Complexity Regularizations: A Localization Result
svaiter
0
66
Low Complexity Regularizations: a Localization Result
svaiter
0
110
Model Selection with Partly Smooth Functions
svaiter
0
38
Low Complexity Models: Robustness
svaiter
0
60
Low Complexity Models: Robustness and Sensivity
svaiter
0
35
Recovery Guarantees for Low Complexity Models
svaiter
1
75
Other Decks in Science
See All in Science
実力評価性能を考慮した弓道高校生全国大会の大会制度設計の提案 / (konakalab presentation at MSS 2025.03)
konakalab
2
180
IWASAKI Hideo
genomethica
0
120
局所保存性・相似変換対称性を満たす機械学習モデルによる数値流体力学
yellowshippo
1
290
データベース09: 実体関連モデル上の一貫性制約
trycycle
PRO
0
980
CV_5_3dVision
hachama
0
140
生成検索エンジン最適化に関する研究の紹介
ynakano
2
1.2k
05_山中真也_室蘭工業大学大学院工学研究科教授_だてプロの挑戦.pdf
sip3ristex
0
560
地質研究者が苦労しながら運用する情報公開システムの実例
naito2000
0
230
データマイニング - ウェブとグラフ
trycycle
PRO
0
140
mathematics of indirect reciprocity
yohm
1
160
コンピュータビジョンによるロボットの視覚と判断:宇宙空間での適応と課題
hf149
0
210
04_石井クンツ昌子_お茶の水女子大学理事_副学長_D_I社会実現へ向けて.pdf
sip3ristex
0
550
Featured
See All Featured
The World Runs on Bad Software
bkeepers
PRO
70
11k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.4k
Become a Pro
speakerdeck
PRO
29
5.5k
Bash Introduction
62gerente
613
210k
Rebuilding a faster, lazier Slack
samanthasiow
83
9.1k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
130
19k
[RailsConf 2023] Rails as a piece of cake
palkan
56
5.7k
A Modern Web Designer's Workflow
chriscoyier
695
190k
Designing Experiences People Love
moore
142
24k
The Pragmatic Product Professional
lauravandoore
36
6.8k
The Language of Interfaces
destraynor
158
25k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
283
13k
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)