activity
20202022
most citedOn Last-Iterate Convergence Beyond Zero-Sum Games

6 citations · 8 across the 4 of their papers we have counts for

collaborators

7 papers

cs.GT20226 cited

On Last-Iterate Convergence Beyond Zero-Sum Games

Ioannis Anagnostides, Ioannis Panageas, Gabriele Farina +1

Most existing results about \emph{last-iterate convergence} of learning dynamics are limited to two-player zero-sum games, and only apply under rigid assumptions about what dynamic…

math.OC2021

Frequency-Domain Representation of First-Order Methods: A Simple and Robust Framework of Analysis

Ioannis Anagnostides, Ioannis Panageas

Motivated by recent applications in min-max optimization, we employ tools from nonlinear control theory in order to analyze a class of "historical" gradient-based methods, for whic…

cs.DC20212 cited

Deterministic Distributed Algorithms and Lower Bounds in the Hybrid Model

Ioannis Anagnostides, Themis Gouleakis

The $\hybrid$ model was recently introduced by Augustine et al. \cite{DBLP:conf/soda/AugustineHKSS20} in order to characterize from an algorithmic standpoint the capabilities of ne…

cs.GT2021

Metric-Distortion Bounds under Limited Information

Ioannis Anagnostides, Dimitris Fotakis, Panagiotis Patsilinakos

In this work we study the metric distortion problem in voting theory under a limited amount of ordinal information. Our primary contribution is threefold. First, we consider mechan…

stat.ML2020

Robust Learning under Strong Noise via SQs

Ioannis Anagnostides, Themis Gouleakis, Ali Marashian

This work provides several new insights on the robustness of Kearns' statistical query framework against challenging label-noise models. First, we build on a recent result by \cite…

math.OC2020

A Robust Framework for Analyzing Gradient-Based Dynamics in Bilinear Games

Ioannis Anagnostides, Paolo Penna

In this work, we establish a frequency-domain framework for analyzing gradient-based algorithms in linear minimax optimization problems; specifically, our approach is based on the…