works on

From the 1 of 22 linked papers with an AI index.

activity
20242026
most citedGemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

47 citations · 48 across the 9 of their papers we have counts for

collaborators
Showing cs.GTShow all

14 papers · 1 filter

cs.GT2026

Paradoxes of Game Theoretic Equilibria and Price of Anarchy

Georgios Piliouras, Ian Gemp, Siqi Liu +1

The paper shows that static equilibrium concepts like Nash and correlated equilibria can hide unstable dynamics in multi‑agent learning, leading to unbounded or chaotic inefficienc…

cs.GT2026

Nash without Numbers: A Social Choice Approach to Mixed Equilibria in Context-Ordinal Games

Ian Gemp, Crystal Qian, Marc Lanctot +1

Nash equilibrium serves as a fundamental mathematical tool in economics and game theory. However, it classically assumes knowledge of player utilities, whereas economics generally…

cs.GT2026

Chaos in Autobidding Auctions

Ioannis Anagnostides, Ian Gemp, Georgios Piliouras +1

As autobidding systems increasingly dominate online advertising auctions, characterizing their long-term dynamical behavior is brought to the fore. In this paper, we examine the dy…

cs.GT2026

Tight Inapproximability for Welfare-Maximizing Autobidding Equilibria

Ioannis Anagnostides, Ian Gemp, Georgios Piliouras +1

We examine the complexity of computing welfare- and revenue-maximizing equilibria in autobidding second-price auctions subject to return-on-spend (RoS) constraints. We show that co…

cs.GT2025

Charting the Shapes of Stories with Game Theory

Constantinos Daskalakis, Ian Gemp, Yanchen Jiang +3

Stories are records of our experiences and their analysis reveals insights into the nature of being human. Successful analyses are often interdisciplinary, leveraging mathematical…

cs.GT2025

Solving Zero-Sum Convex Markov Games

Fivos Kalogiannis, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Ian Gemp +1

We contribute the first provable guarantees of global convergence to Nash equilibria (NE) in two-player zero-sum convex Markov games (cMGs) by using independent policy gradient met…