paper-with-me

홈 › Papers

An accelerated first-order regularized momentum descent ascent algorithm for stochastic nonconvex-concave minimax problems

2023-10-24 · Huiling Zhang, Zi Xu

Stochastic nonconvex minimax problems have attracted wide attention in machine learning, signal processing and many other fields in recent years. In this paper, we propose an accelerated first-order regularized momentum descent ascent algorithm (FORMDA) for solving stochastic nonconvex-concave minimax problems. The iteration complexity of the algorithm is proved to be $\tilde{\mathcal{O}}(\varepsilon ^{-6.5})$ to obtain an $\varepsilon$-stationary point, which achieves the best-known complexity bound for single-loop algorithms to solve the stochastic nonconvex-concave minimax problems under the stationarity of the objective function.

📄 PDF Abstract BibTeX arXiv:2310.15448

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Accelerated Zeroth-Order and First-Order Momentum Methods from Mini to Minimax Optimization

2020-08-18 · Feihu Huang, Shangqian Gao, Jian Pei, Heng Huang

In the paper, we propose a class of accelerated zeroth-order and first-order momentum methods for both nonconvex mini-optimization and minimax-optimization. Specifically, we propose a new accelerated zeroth-order momentu…

Adversarial Attack

Stochastic Subspace Cubic Newton Method

2020-02-21 · ICML 2020 1 · Filip Hanzely, Nikita Doikov, Peter Richtárik, Yurii Nesterov

In this paper, we propose a new randomized second-order optimization algorithm---Stochastic Subspace Cubic Newton (SSCN)---for minimizing a high dimensional convex function $f$. Our method can be seen both as a {\em stoc…

Second-order methods

Accelerating Asynchronous Algorithms for Convex Optimization by Momentum Compensation

2018-02-27 · Cong Fang, Yameng Huang, Zhouchen Lin

Asynchronous algorithms have attracted much attention recently due to the crucial demands on solving large-scale optimization problems. However, the accelerated versions of asynchronous algorithms are rarely studied. In …

Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent

2023-02-02 · Avrajit Ghosh, He Lyu, Xitong Zhang, Rongrong Wang

It is well known that the finite step-size ($h$) in Gradient Descent (GD) implicitly regularizes solutions to flatter minima. A natural question to ask is "Does the momentum parameter $\beta$ play a role in implicit regu…

Accelerated Proximal Alternating Gradient-Descent-Ascent for Nonconvex Minimax Machine Learning

2021-12-22 · Ziyi Chen, Shaocong Ma, Yi Zhou

Alternating gradient-descent-ascent (AltGDA) is an optimization algorithm that has been widely used for model training in various machine learning applications, which aims to solve a nonconvex minimax optimization proble…

BIG-bench Machine Learning