In this work, we introduce a new variant of online gradient descent, whi...
The works of (Daskalakis et al., 2009, 2022; Jin et al., 2022; Deng et a...
Most of the literature on learning in games has focused on the restricti...
Adversarial team games model multiplayer strategic interactions in which...
Recurrent Neural Networks (RNNs) frequently exhibit complicated dynamics...
Computing Nash equilibrium policies is a central problem in multi-agent
...
We consider non-convex optimization problems with constraint that is a
p...
We show that, for any sufficiently small fixed ϵ > 0, when both
players ...
Most existing results about last-iterate convergence of learning
dynamic...
Motivated by recent advances in both theoretical and applied aspects of
...
Multi-agent reinforcement learning has been successfully applied to
full...
This paper is an attempt to deal with the recent realization (Vazirani,
...
Potential games are arguably one of the most important and widely studie...
Sampling is a fundamental and arguably very important task with numerous...
In this paper, we study high-dimensional estimation from truncated sampl...
Spin glass models, such as the Sherrington-Kirkpatrick, Hopfield and Isi...
The expressivity of neural networks as a function of their depth, width ...
Non-negative matrix factorization (NMF) is a fundamental non-convex
opti...
In a recent series of papers it has been established that variants of
Gr...
Understanding the representational power of Deep Neural Networks (DNNs) ...
The standard linear and logistic regression models assume that the respo...
Motivated by a recent result of Daskalakis et al. DGTZ18, we analyze
the...
Motivated by applications in Game Theory, Optimization, and Generative
A...
Motivated by applications in Optimization, Game Theory, and the training...
We model a situation in which a collection of species derive their fitne...
We establish that first-order methods avoid saddle points for almost all...