Sublinear convergence rates of extragradient-type methods: A survey on classical and recent developments
Q Tran-Dinh - arXiv preprint arXiv:2303.17192, 2023 - arxiv.org
The extragradient (EG), introduced by GM Korpelevich in 1976, is a well-known method to
approximate solutions of saddle-point problems and their extensions such as variational …
approximate solutions of saddle-point problems and their extensions such as variational …
Convergence of proximal point and extragradient-based methods beyond monotonicity: the case of negative comonotonicity
Algorithms for min-max optimization and variational inequalities are often studied under
monotonicity assumptions. Motivated by non-monotone machine learning applications, we …
monotonicity assumptions. Motivated by non-monotone machine learning applications, we …
Last-iterate convergent policy gradient primal-dual methods for constrained mdps
We study the problem of computing an optimal policy of an infinite-horizon discounted
constrained Markov decision process (constrained MDP). Despite the popularity of …
constrained Markov decision process (constrained MDP). Despite the popularity of …
Stable nonconvex-nonconcave training via linear interpolation
This paper presents a theoretical analysis of linear interpolation as a principled method for
stabilizing (large-scale) neural network training. We argue that instabilities in the …
stabilizing (large-scale) neural network training. We argue that instabilities in the …
Accelerated single-call methods for constrained min-max optimization
We study first-order methods for constrained min-max optimization. Existing methods either
require two gradient calls or two projections in each iteration, which may be costly in some …
require two gradient calls or two projections in each iteration, which may be costly in some …
Solving nonconvex-nonconcave min-max problems exhibiting weak minty solutions
A Böhm - arXiv preprint arXiv:2201.12247, 2022 - arxiv.org
We investigate a structured class of nonconvex-nonconcave min-max problems exhibiting
so-called\emph {weak Minty} solutions, a notion which was only recently introduced, but is …
so-called\emph {weak Minty} solutions, a notion which was only recently introduced, but is …
Doubly optimal no-regret learning in monotone games
We consider online learning in multi-player smooth monotone games. Existing algorithms
have limitations such as (1) being only applicable to strongly monotone games;(2) lacking …
have limitations such as (1) being only applicable to strongly monotone games;(2) lacking …
On the interplay between social welfare and tractability of equilibria
I Anagnostides, T Sandholm - Advances in Neural …, 2024 - proceedings.neurips.cc
Computational tractability and social welfare (aka. efficiency) of equilibria are two
fundamental but in general orthogonal considerations in algorithmic game theory …
fundamental but in general orthogonal considerations in algorithmic game theory …
Universal gradient descent ascent method for nonconvex-nonconcave minimax optimization
Nonconvex-nonconcave minimax optimization has received intense attention over the last
decade due to its broad applications in machine learning. Most existing algorithms rely on …
decade due to its broad applications in machine learning. Most existing algorithms rely on …
Variance reduced halpern iteration for finite-sum monotone inclusions
Machine learning approaches relying on such criteria as adversarial robustness or multi-
agent settings have raised the need for solving game-theoretic equilibrium problems. Of …
agent settings have raised the need for solving game-theoretic equilibrium problems. Of …