中文
相关论文

相关论文: Second-Order Mirror Descent: Convergence in Games …

200 篇论文

Saddle point problems, ubiquitous in optimization, extend beyond game theory to diverse domains like power networks and reinforcement learning. This paper presents novel approaches to tackle saddle point problem, with a focus on…

最优化与控制 · 数学 2024-04-09 Anik Kumar Paul , Arun D Mahindrakar , Rachel K Kalaimani

In this paper, we investigate the non-asymptotic stationary convergence behavior of Stochastic Mirror Descent (SMD) for nonconvex optimization. We focus on a general class of nonconvex nonsmooth stochastic optimization problems, in which…

最优化与控制 · 数学 2018-06-14 Siqi Zhang , Niao He

Smoothness is crucial for attaining fast rates in first-order optimization. However, many optimization problems in modern machine learning involve non-smooth objectives. Recent studies relax the smoothness assumption by allowing the…

最优化与控制 · 数学 2026-02-11 Dingzhi Yu , Wei Jiang , Hongyi Tao , Yuanyu Wan , Lijun Zhang

Online mirror descent (OMD) and dual averaging (DA) -- two fundamental algorithms for online convex optimization -- are known to have very similar (and sometimes identical) performance guarantees when used with a fixed learning rate. Under…

机器学习 · 计算机科学 2021-09-07 Huang Fang , Nicholas J. A. Harvey , Victor S. Portella , Michael P. Friedlander

Mirror descent is a well established tool for solving convex optimization problems with convex constraints. This article introduces continuous-time mirror descent dynamics for approximating optimal Markov controls for stochastic control…

最优化与控制 · 数学 2025-06-04 Deven Sethi , David Šiška

We study two variants of the mirror descent-ascent (MDA) algorithm for solving min-max problems on the space of measures: simultaneous and alternating. We work under assumptions of convexity-concavity and relative smoothness of the payoff…

最优化与控制 · 数学 2026-05-08 Razvan-Andrei Lascu , Mateusz B. Majka , Łukasz Szpruch

We investigate the convergence of stochastic mirror descent (SMD) under interpolation in relatively smooth and smooth convex optimization. In relatively smooth convex optimization we provide new convergence guarantees for SMD with a…

最优化与控制 · 数学 2023-05-26 Ryan D'Orazio , Nicolas Loizou , Issam Laradji , Ioannis Mitliagkas

Different types of dynamics have been studied in repeated game play, and one of them which has received much attention recently consists of those based on "no-regret" algorithms from the area of machine learning. It is known that dynamics…

计算机科学与博弈论 · 计算机科学 2016-10-14 Po-An Chen , Chi-Jen Lu

Stochastic mirror descent (SMD) is a fairly new family of algorithms that has recently found a wide range of applications in optimization, machine learning, and control. It can be considered a generalization of the classical stochastic…

最优化与控制 · 数学 2019-04-04 Navid Azizan , Babak Hassibi

It is well known that mirror descent may diverge or cycle on merely monotone variational inequalities. In this paper, we propose \emph{Target Mirror Descent} (TMD), a unified framework that stabilizes monotone flows via a target point…

最优化与控制 · 数学 2026-04-22 Yu-Wen Chen , Can Kizilkale , Murat Arcak

We show that, for any sufficiently small fixed $\epsilon > 0$, when both players in a general-sum two-player (bimatrix) game employ optimistic mirror descent (OMD) with smooth regularization, learning rate $\eta = O(\epsilon^2)$ and $T =…

计算机科学与博弈论 · 计算机科学 2022-10-10 Ioannis Anagnostides , Gabriele Farina , Ioannis Panageas , Tuomas Sandholm

This paper revisits the convergence of Stochastic Mirror Descent (SMD) in the contemporary nonconvex optimization setting. Existing results for batch-free nonconvex SMD restrict the choice of the distance generating function (DGF) to be…

最优化与控制 · 数学 2024-02-28 Ilyas Fatkhullin , Niao He

In this paper, the optimal convergence rate $O\left(N^{-1/2}\right)$ (where $N$ is the total number of iterations performed by the algorithm), without the presence of a logarithmic factor, is proved for mirror descent algorithms with…

最优化与控制 · 数学 2025-06-04 Mohammad Alkousa , Fedor Stonyakin , Asmaa Abdo , Mohammad Alcheikh

We study the problem of no-regret learning algorithms for general monotone and smooth games and their last-iterate convergence properties. Specifically, we investigate the problem under bandit feedback and strongly uncoupled dynamics, which…

计算机科学与博弈论 · 计算机科学 2024-08-19 Jing Dong , Baoxiang Wang , Yaoliang Yu

Recent work by Woodworth et al. (2020) shows that the optimization dynamics of gradient descent for overparameterized problems can be viewed as low-dimensional dual dynamics induced by a mirror map, explaining the implicit regularization…

机器学习 · 计算机科学 2024-10-21 Shuyang Wang , Diego Klabjan

We study how to learn $\epsilon$-optimal strategies in zero-sum imperfect information games (IIG) with trajectory feedback. In this setting, players update their policies sequentially based on their observations over a fixed number of…

计算机科学与博弈论 · 计算机科学 2023-09-06 Côme Fiegel , Pierre Ménard , Tadashi Kozuno , Rémi Munos , Vianney Perchet , Michal Valko

Inspired by the remarkable success of large neural networks, there has been significant interest in understanding the generalization performance of over-parameterized models. Substantial efforts have been invested in characterizing how…

机器学习 · 计算机科学 2024-01-12 Haoyuan Sun , Khashayar Gatmiry , Kwangjun Ahn , Navid Azizan

We introduce an inexact variant of Stochastic Mirror Descent (SMD), called Inexact Stochastic Mirror Descent (ISMD), to solve nonlinear two-stage stochastic programs where the second stage problem has linear and nonlinear coupling…

最优化与控制 · 数学 2020-06-30 Vincent Guigues

In recent years, attention has been focused on the relationship between black-box optimiza- tion problem and reinforcement learning problem. In this research, we propose the Mirror Descent Search (MDS) algorithm which is applicable both for…

机器学习 · 计算机科学 2018-05-15 Megumi Miyashita , Shiro Yano , Toshiyuki Kondo

The mirror descent algorithm is known to be effective in situations where it is beneficial to adapt the mirror map to the underlying geometry of the optimization model. However, the effect of mirror maps on the geometry of distributed…

最优化与控制 · 数学 2024-03-13 Anastasia Borovykh , Nikolas Kantas , Panos Parpas , Grigorios A. Pavliotis