3 papers
cs.GT2026
Structure from Strategic Interaction & Uncertainty: Risk Sensitive Games for Robust Preference Learning
Max Horwitz, Jake Gonzales, Eric Mazumdar +1
A growing line of work reframes preference-based fine-tuning of large language models game-theoretically: Nash Learning from Human Feedback (NLHF) recasts the problem as a zero-sum…
cs.LG2026
Strategically Robust Multi-Agent Reinforcement Learning with Linear Function Approximation
Jake Gonzales, Max Horwitz, Eric Mazumdar +1
Provably efficient and robust equilibrium computation in general-sum Markov games remains a core challenge in multi-agent reinforcement learning. Nash equilibrium is computationall…
math.CO2025
Obtaining the Chamanara Surface from the van der Corput sequence
Zawad Chowdhury, Francois Clement, Max Horwitz
We investigate a family of -regular graphs constructed to test for the presence of combinatorial structure in a sequence of distinct real numbers. We show that the graphs constr…