paper-with-me

Papers

Primal-Dual Sequential Subspace Optimization for Saddle-point Problems

2020-08-20 · Yoni Choukroun, Michael Zibulevsky, Pavel Kisilev

We introduce a new sequential subspace optimization method for large-scale saddle-point problems. It solves iteratively a sequence of auxiliary saddle-point problems in low-dimensional subspaces, spanned by directions derived from first-order information over the primal \emph{and} dual variables. Proximal regularization is further deployed to stabilize the optimization process. Experimental results demonstrate significantly better convergence relative to popular first-order methods. We analyze the influence of the subspace on the convergence of the algorithm, and assess its performance in various deterministic optimization scenarios, such as bi-linear games, ADMM-based constrained optimization and generative adversarial networks.

📄 PDF Abstract BibTeX arXiv:2008.09149

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Federated Composite Saddle Point Optimization

2023-05-25 · Site Bai, Brian Bullins

Federated learning (FL) approaches for saddle point problems (SPP) have recently gained in popularity due to the critical role they play in machine learning (ML). Existing works mostly target smooth unconstrained objecti…

Federated Learning

Dual SVM Training on a Budget

2018-06-26 · Sahar Qaadan, Merlin Schüler, Tobias Glasmachers

We present a dual subspace ascent algorithm for support vector machine training that respects a budget constraint limiting the number of support vectors. Budget methods are effective for reducing the training time of ker…

Doubly Stochastic Primal-Dual Coordinate Method for Bilinear Saddle-Point Problem

2015-08-14 · Adams Wei Yu, Qihang Lin, Tianbao Yang

We propose a doubly stochastic primal-dual coordinate optimization algorithm for empirical risk minimization, which can be formulated as a bilinear saddle-point problem. In each iteration, our method randomly samples a b…

Provable Last-Iterate Convergence for Multi-Objective Safe LLM Alignment via Optimistic Primal-Dual

2026-02-25 · Yining Li, Peizhong Ju, Ness Shroff arxiv

Reinforcement Learning from Human Feedback (RLHF) plays a significant role in aligning Large Language Models (LLMs) with human preferences. While RLHF with expected reward constraints can be formulated as a primal-dual o…

Reinforcement Learning

Stochastic Parallel Block Coordinate Descent for Large-scale Saddle Point Problems

2015-11-23 · Zhanxing Zhu, Amos J. Storkey

We consider convex-concave saddle point problems with a separable structure and non-strongly convex functions. We propose an efficient stochastic block coordinate descent method using adaptive primal-dual updates, which …

feature selection