
Teamwork makes von Neumann work: MinMax Optimization in TwoTeam ZeroSum Games
Motivated by recent advances in both theoretical and applied aspects of ...
read it

Independent Natural Policy Gradient Always Converges in Markov Potential Games
Multiagent reinforcement learning has been successfully applied to full...
read it

Combinatorial Algorithms for Matching Markets via Nash Bargaining: OneSided, TwoSided and NonBipartite
This paper is an attempt to deal with the recent realization (Vazirani, ...
read it

Global Convergence of MultiAgent Policy Gradient in Markov Potential Games
Potential games are arguably one of the most important and widely studie...
read it

Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet LogSobolev
Sampling is a fundamental and arguably very important task with numerous...
read it

Efficient Statistics for Sparse Graphical Models from Truncated Samples
In this paper, we study highdimensional estimation from truncated sampl...
read it

LogisticRegression with peergroup effects via inference in higher order Ising models
Spin glass models, such as the SherringtonKirkpatrick, Hopfield and Isi...
read it

Better DepthWidth Tradeoffs for Neural Networks through the lens of Dynamical Systems
The expressivity of neural networks as a function of their depth, width ...
read it

Convergence to SecondOrder Stationarity for Nonnegative Matrix Factorization: Provably and Concurrently
Nonnegative matrix factorization (NMF) is a fundamental nonconvex opti...
read it

Last iterate convergence in noregret learning: constrained minmax optimization for convexconcave landscapes
In a recent series of papers it has been established that variants of Gr...
read it

DepthWidth Tradeoffs for ReLU Networks via Sharkovsky's Theorem
Understanding the representational power of Deep Neural Networks (DNNs) ...
read it

Regression from Dependent Observations
The standard linear and logistic regression models assume that the respo...
read it

On the Convergence of EM for truncated mixtures of two Gaussians
Motivated by a recent result of Daskalakis et al. DGTZ18, we analyze the...
read it

LastIterate Convergence: ZeroSum Games and Constrained MinMax Optimization
Motivated by applications in Game Theory, Optimization, and Generative A...
read it

The Limit Points of (Optimistic) Gradient Descent in MinMax Optimization
Motivated by applications in Optimization, Game Theory, and the training...
read it

RockPaperScissors, Differential Games and Biological Diversity
We model a situation in which a collection of species derive their fitne...
read it

Firstorder Methods Almost Always Avoid Saddle Points
We establish that firstorder methods avoid saddle points for almost all...
read it
Ioannis Panageas
is this you? claim profile