English
Related papers

Related papers: Acceleration through Optimistic No-Regret Dynamics

200 papers

We consider the problem of simultaneous learning in stochastic games with many players in the finite-horizon setting. While the typical target solution for a stochastic game is a Nash equilibrium, this is intractable with many players. We…

Computer Science and Game Theory · Computer Science 2022-10-27 William Brown

Extensive-form games are a common model for multiagent interactions with imperfect information. In two-player zero-sum games, the typical solution concept is a Nash equilibrium over the unconstrained strategy set for each player. In many…

Computer Science and Game Theory · Computer Science 2019-02-07 Trevor Davis , Kevin Waugh , Michael Bowling

Momentum methods for convex optimization often rely on precise choices of algorithmic parameters, based on knowledge of problem parameters, in order to achieve fast convergence, as well as to prevent oscillations that could severely…

Systems and Control · Electrical Eng. & Systems 2021-03-24 Justin H. Le , Andrew R. Teel

We introduce Cut-and-Play, a practically-efficient algorithm for computing Nash equilibria in simultaneous non-cooperative games where players decide via nonconvex and possibly unbounded optimization problems with separable payoff…

Optimization and Control · Mathematics 2024-05-06 Margarida Carvalho , Gabriele Dragotto , Andrea Lodi , Sriram Sankaranarayanan

Our work focuses on extra gradient learning algorithms for finding Nash equilibria in bilinear zero-sum games. The proposed method, which can be formally considered as a variant of Optimistic Mirror Descent…

Computer Science and Game Theory · Computer Science 2022-03-09 Michail Fasoulakis , Evangelos Markakis , Yannis Pantazis , Constantinos Varsos

Min-max saddle point games appear in a wide range of applications in machine leaning and signal processing. Despite their wide applicability, theoretical studies are mostly limited to the special convex-concave structure. While some recent…

Optimization and Control · Mathematics 2020-03-19 Babak Barazandeh , Meisam Razaviyayn

Quasar convexity is a condition that allows some first-order methods to efficiently minimize a function even when the optimization landscape is non-convex. Previous works develop near-optimal accelerated algorithms for minimizing this class…

Optimization and Control · Mathematics 2023-02-16 Jun-Kun Wang , Andre Wibisono

For a linear equality constrained convex optimization problem involving two objective functions with a ``nonsmooth" + ``nonsmooth" composite structure, we study two algorithms derived from a mixed-order dynamical system which incorporates…

Optimization and Control · Mathematics 2026-03-25 Geng-Hua Li , Hai-Yi Zhao , Xiangkai Sun

We propose a penalty-based smoothing framework for convex nonsmooth functions with a supremum structure. The regularization yields a differentiable surrogate with controlled approximation error, a single-valued dual maximizer, and explicit…

Optimization and Control · Mathematics 2026-01-22 Samir Adly , Juan José Maulén , Emilio Vilches

In this paper, we consider two-player zero-sum matrix and stochastic games and develop learning dynamics that are payoff-based, convergent, rational, and symmetric between the two players. Specifically, the learning dynamics for matrix…

Machine Learning · Computer Science 2024-09-06 Zaiwei Chen , Kaiqing Zhang , Eric Mazumdar , Asuman Ozdaglar , Adam Wierman

We propose a hierarchical version of dual averaging for zeroth-order online non-convex optimization - i.e., learning processes where, at each stage, the optimizer is facing an unknown non-convex loss function and only receives the incurred…

Machine Learning · Computer Science 2021-09-14 Amélie Héliou , Matthieu Martin , Panayotis Mertikopoulos , Thibaud Rahier

Hoffman's classical result gives a bound on the distance of a point from a convex and compact polytope in terms of the magnitude of violation of the constraints. Recently, several results showed that Hoffman's bound can be used to derive…

Machine Learning · Computer Science 2019-02-19 Dan Garber

We develop two new proximal alternating penalty algorithms to solve a wide range class of constrained convex optimization problems. Our approach mainly relies on a novel combination of the classical quadratic penalty, alternating…

Optimization and Control · Mathematics 2018-09-20 Quoc Tran-Dinh

Recent literature on online learning has focused on developing adaptive algorithms that take advantage of a regularity of the sequence of observations, yet retain worst-case performance guarantees. A complementary direction is to develop…

Machine Learning · Computer Science 2015-01-27 Ali Jadbabaie , Alexander Rakhlin , Shahin Shahrampour , Karthik Sridharan

We consider the stochastic approximation problem where a convex function has to be minimized, given only the knowledge of unbiased estimates of its gradients at certain points, a framework which includes machine learning methods based on…

Machine Learning · Computer Science 2013-06-11 Francis Bach , Eric Moulines

We study the problem of learning a Nash equilibrium (NE) in Markov games which is a cornerstone in multi-agent reinforcement learning (MARL). In particular, we focus on infinite-horizon adversarial team Markov games (ATMGs) in which agents…

Computer Science and Game Theory · Computer Science 2024-10-10 Fivos Kalogiannis , Jingming Yan , Ioannis Panageas

The study of learning in games has thus far focused primarily on normal form games. In contrast, our understanding of learning in extensive form games (EFGs) and particularly in EFGs with many agents lags far behind, despite them being…

Computer Science and Game Theory · Computer Science 2022-07-19 Georgios Piliouras , Lillian Ratliff , Ryann Sim , Stratis Skoulakis

In a recent series of papers it has been established that variants of Gradient Descent/Ascent and Mirror Descent exhibit last iterate convergence in convex-concave zero-sum games. Specifically, \cite{DISZ17, LiangS18} show last iterate…

Machine Learning · Computer Science 2025-09-30 Qi Lei , Sai Ganesh Nagarajan , Ioannis Panageas , Xiao Wang

We develop a reduction-based framework for online learning with delayed feedback that recovers and improves upon existing results for both first-order and bandit convex optimization. Our approach introduces a continuous-time model under…

Machine Learning · Computer Science 2026-02-04 Alexander Ryabchenko , Idan Attias , Daniel M. Roy

We revisit the problem of \textit{online linear optimization} in case the set of feasible actions is accessible through an approximated linear optimization oracle with a factor $\alpha$ multiplicative approximation guarantee. This setting…

Machine Learning · Computer Science 2017-09-12 Dan Garber
‹ Prev 1 8 9 10 Next ›