paper-with-me

홈 › Papers

Asymptotics of Proximity Operator for Squared Loss and Performance Prediction of Nonconvex Sparse Signal Recovery

2021-03-18 · Ryo Hayakawa

Proximal splitting-based convex optimization is a promising approach to linear inverse problems because we can use some prior knowledge of the unknown variables explicitly. An understanding of the behavior of the optimization algorithms would be important for the tuning of the parameters and the development of new algorithms. In this paper, we first analyze the asymptotic property of the proximity operator for the squared loss function, which appears in the update equations of some proximal splitting methods for linear inverse problems. Our analysis shows that the output of the proximity operator can be characterized with a scalar random variable in the large system limit. Moreover, we apply the asymptotic result to the prediction of optimization algorithms for compressed sensing. Simulation results demonstrate that the MSE performance of the Douglas-Rachford algorithm can be well predicted in compressed sensing with the $\ell_{1}$ optimization. We also examine the behavior of the prediction for the case with nonconvex smoothly clipped absolute deviation (SCAD) and minimax concave penalty (MCP) regularization.

📄 PDF Abstract BibTeX arXiv:2103.10300

Code (0)

등록된 구현이 없습니다.

Tasks

compressed sensing

Similar Papers 제목 키워드 기반

Mack's estimator motivated by large exposure asymptotics in a compound Poisson setting

2023-10-18 · Nils Engler, Filip Lindskog

The distribution-free chain ladder of Mack justified the use of the chain ladder predictor and enabled Mack to derive an estimator of conditional mean squared error of prediction for the chain ladder predictor. Classical…

Prediction

Robust Low-Rank Matrix Completion via a New Sparsity-Inducing Regularizer

2023-10-07 · Zhi-Yong Wang, Hing Cheung So, Abdelhak M. Zoubir

This paper presents a novel loss function referred to as hybrid ordinary-Welsch (HOW) and a new sparsity-inducing regularizer associated with HOW. We theoretically show that the regularizer is quasiconvex and that the co…

Low-Rank Matrix CompletionMatrix Completion

Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning

2026-02-19 · Hien Dang, Pratik Patil, Alessandro Rinaldo arxiv

Self-distillation (SD) is the process of retraining a student on a mixture of ground-truth labels and the teacher's own predictions using the same architecture and training data. Although SD has been empirically shown to…

Learning to solve inverse problems using Wasserstein loss

2017-10-30 · Jonas Adler, Axel Ringh, Ozan Öktem, Johan Karlsson

We propose using the Wasserstein loss for training in inverse problems. In particular, we consider a learned primal-dual reconstruction scheme for ill-posed inverse problems using the Wasserstein distance as loss functio…

Spectral k-Support Norm Regularization

2014-12-01 · NeurIPS 2014 12 · Andrew M. McDonald, Massimiliano Pontil, Dimitris Stamos

The $k$-support norm has successfully been applied to sparse vector prediction problems. We observe that it belongs to a wider class of norms, which we call the box-norms. Within this framework we derive an efficient alg…

Matrix Completion