Convergence of the Min-Max Langevin Dynamics and Algorithm for Zero-Sum Games

Y Cai, S Mitra, X Wang, A Wibisono - arxiv preprint arxiv:2412.20471, 2024 - arxiv.org
We study zero-sum games in the space of probability distributions over the Euclidean space
$\mathbb {R}^ d $ with entropy regularization, in the setting when the interaction function …

Convergence of two-timescale gradient descent ascent dynamics: finite-dimensional and mean-field perspectives

J An, J Lu - arxiv preprint arxiv:2501.17122, 2025 - arxiv.org
The two-timescale gradient descent-ascent (GDA) is a canonical gradient algorithm
designed to find Nash equilibria in min-max games. We analyze the two-timescale GDA by …