Performative prediction is a framework for learning models that influence the data they intend to predict. We focus on finding classifiers that are performatively stable, ie optimal for …
We study the problem of learning a Nash equilibrium (NE) in Markov games which is a cornerstone in multi-agent reinforcement learning (MARL). In particular, we focus on infinite …
In this work, we consider constrained stochastic optimization problems under hidden convexity, ie, those that admit a convex reformulation via non-linear (but invertible) map $ c …
A wide array of modern machine learning applications–from adversarial models to multi- agent reinforcement learning–can be formulated as non-cooperative games whose Nash …
Deep learning has proven to be effective in a wide variety of loss minimization problems. However, many applications of interest, like minimizing projected Bellman error and min …
J Müller, M Zeinhofer - Forty-first International Conference on Machine … - openreview.net
We provide an infinite-dimensional view on optimization problems encountered in scientific machine learning (SciML) and advocate for the paradigm first optimize, then discretize for …
This thesis explores minimax formulations of machine learning and multi-agent learning problems, focusing on algorithmic optimization and generalization performance. The first …