paper-with-me

Papers

Frank-Wolfe Algorithms for Saddle Point Problems

2016-10-25 · Gauthier Gidel, Tony Jebara, Simon Lacoste-Julien

We extend the Frank-Wolfe (FW) optimization algorithm to solve constrained smooth convex-concave saddle point (SP) problems. Remarkably, the method only requires access to linear minimization oracles. Leveraging recent advances in FW optimization, we provide the first proof of convergence of a FW-type saddle point solver over polytopes, thereby partially answering a 30 year-old conjecture. We also survey other convergence results and highlight gaps in the theoretical underpinnings of FW-style algorithms. Motivating applications without known efficient alternatives are explored through structured prediction with combinatorial penalties as well as games over matching polytopes involving an exponential number of constraints.

📄 PDF Abstract BibTeX arXiv:1610.07797

Code (3)

MindCode-4/code-12/tree/main/Frank-Wolfe-Algorithm mindspore
MindCode-4/code-7/tree/main/Frank-Wolfe-Algorithm mindspore
mustafakarabag/sp-admm

Tasks

Structured Prediction

Similar Papers 제목 키워드 기반

Online and Bandit Algorithms for Nonstationary Stochastic Saddle-Point Optimization

2019-12-03 · Abhishek Roy, Yifang Chen, Krishnakumar Balasubramanian, Prasant Mohapatra

Saddle-point optimization problems are an important class of optimization problems with applications to game theory, multi-agent reinforcement learning and machine learning. A majority of the rich literature available fo…

Multi-agent Reinforcement LearningReinforcement Learning

Efficient Projection-Free Algorithms for Saddle Point Problems

2020-10-21 · NeurIPS 2020 12 · Cheng Chen, Luo Luo, Weinan Zhang, Yong Yu

The Frank-Wolfe algorithm is a classic method for constrained optimization problems. It has recently been popular in many machine learning applications because its projection-free property leads to more efficient iterati…

On Frank-Wolfe and Equilibrium Computation

2017-12-01 · NeurIPS 2017 12 · Jacob D. Abernethy, Jun-Kun Wang

We consider the Frank-Wolfe (FW) method for constrained convex optimization, and we show that this classical technique can be interpreted from a different perspective: FW emerges as the computation of an equilibrium (sad…

Understanding Modern Techniques in Optimization: Frank-Wolfe, Nesterov's Momentum, and Polyak's Momentum

2021-06-23 · Jun-Kun Wang

In the first part of this dissertation research, we develop a modular framework that can serve as a recipe for constructing and analyzing iterative algorithms for convex optimization. Specifically, our work casts optimiz…

Frank-Wolfe Style Algorithms for Large Scale Optimization

2018-08-15 · Lijun Ding, Madeleine Udell

We introduce a few variants on Frank-Wolfe style algorithms suitable for large scale optimization. We show how to modify the standard Frank-Wolfe algorithm using stochastic gradients, approximate subproblem solutions, an…