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