paper-with-me

Papers

A block-coordinate descent framework for non-convex composite optimization. Application to sparse precision matrix estimation

2026-01-29 · Guillaume Lauga arxiv

Block-coordinate descent (BCD) is the method of choice to solve numerous large scale optimization problems, however their theoretical study for non-convex optimization, has received less attention. In this paper, we present a new block-coordinate descent (BCD) framework to tackle non-convex composite optimization problems, ensuring decrease of the objective function and convergence to a solution. This framework is general enough to include variable metric proximal gradient updates, proximal Newton updates, and alternated minimization updates. This generality allows to encompass three versions of the most used solvers in the sparse precision matrix estimation problem, deemed Graphical Lasso: graphical ISTA, Primal GLasso, and QUIC. We demonstrate the value of this new framework on non-convex sparse precision matrix estimation problems, providing convergence guarantees and up to a $100$-fold reduction in the number of iterations required to reach state-of-the-art estimation quality.

📄 PDF Abstract BibTeX arXiv:2601.21467

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Cyclic Block Coordinate Descent With Variance Reduction for Composite Nonconvex Optimization

2022-12-09 · Xufeng Cai, Chaobing Song, Stephen J. Wright, Jelena Diakonikolas

Nonconvex optimization is central in solving many machine learning problems, in which block-wise structure is commonly encountered. In this work, we propose cyclic block coordinate methods for nonconvex optimization prob…

Randomized Bregman Coordinate Descent Methods for Non-Lipschitz Optimization

2020-01-15 · Tianxiang Gao, Songtao Lu, Jia Liu, Chris Chu

We propose a new \textit{randomized Bregman (block) coordinate descent} (RBCD) method for minimizing a composite problem, where the objective function could be either convex or nonconvex, and the smooth part are freed fr…

Translation

Randomized Block Coordinate Descent for Online and Stochastic Optimization

2014-07-01 · Huahua Wang, Arindam Banerjee

Two types of low cost-per-iteration gradient descent methods have been extensively studied in parallel. One is online or stochastic gradient descent (OGD/SGD), and the other is randomzied coordinate descent (RBCD). In th…

Stochastic Optimization

Asynchronous Stochastic Block Coordinate Descent with Variance Reduction

2016-10-29 · Bin Gu, Zhouyuan Huo, Heng Huang

Asynchronous parallel implementations for stochastic optimization have received huge successes in theory and practice recently. Asynchronous implementations with lock-free are more efficient than the one with writing or …

Stochastic Optimization

Efficiency of Coordinate Descent Methods For Structured Nonconvex Optimization

2019-09-03 · Qi Deng, Chenghao Lan

Novel coordinate descent (CD) methods are proposed for minimizing nonconvex functions consisting of three terms: (i) a continuously differentiable term, (ii) a simple convex term, and (iii) a concave and continuous term.…