The Nonconvex Geometry of Linear Inverse Problems

01/07/2021
by   Armin Eftekhari, et al.
0

The gauge function, closely related to the atomic norm, measures the complexity of a statistical model, and has found broad applications in machine learning and statistical signal processing. In a high-dimensional learning problem, the gauge function attempts to safeguard against overfitting by promoting a sparse (concise) representation within the learning alphabet. In this work, within the context of linear inverse problems, we pinpoint the source of its success, but also argue that the applicability of the gauge function is inherently limited by its convexity, and showcase several learning problems where the classical gauge function theory fails. We then introduce a new notion of statistical complexity, gauge_p function, which overcomes the limitations of the gauge function. The gauge_p function is a simple generalization of the gauge function that can tightly control the sparsity of a statistical model within the learning alphabet and, perhaps surprisingly, draws further inspiration from the Burer-Monteiro factorization in computational mathematics. We also propose a new learning machine, with the building block of gauge_p function, and arm this machine with a number of statistical guarantees. The potential of the proposed gauge_p function theory is then studied for two stylized applications. Finally, we discuss the computational aspects and, in particular, suggest a tractable numerical algorithm for implementing the new learning machine.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/08/2021

Variational Regularization in Inverse Problems and Machine Learning

This paper discusses basic results and recent developments on variationa...
research
09/27/2021

Deformed logarithms. Associated entropic divergences. Applications to linear inverse problems. Inversion algorithms

This work belongs to the framework of inverse problems with linear model...
research
06/20/2017

First Order Methods beyond Convexity and Lipschitz Gradient Continuity with Applications to Quadratic Inverse Problems

We focus on nonconvex and nonsmooth minimization problems with a composi...
research
12/05/2019

Rademacher complexity and spin glasses: A link between the replica and statistical theories of learning

Statistical learning theory provides bounds of the generalization gap, u...
research
10/02/2014

Proceedings of the second "international Traveling Workshop on Interactions between Sparse models and Technology" (iTWIST'14)

The implicit objective of the biennial "international - Traveling Worksh...
research
03/15/2018

Maxiset point of view for signal detection in inverse problems

This paper extends the successful maxiset paradigm from function estimat...
research
06/26/2017

Optimal choice: new machine learning problem and its solution

The task of learning to pick a single preferred example out a finite set...

Please sign up or login with your details

Forgot password? Click here to reset