Schrödinger bridges (SBs) provide an elegant framework for modeling the
...
Diffusion Schrödinger bridges (DSB) have recently emerged as a powerful
...
Non-convex sampling is a key challenge in machine learning, central to
n...
Algorithms that solve zero-sum games, multi-objective agent objectives, ...
Many important learning algorithms, such as stochastic gradient methods,...
We develop a unified stochastic approximation framework for analyzing th...
We propose a new framework to reconstruct a stochastic process
{ℙ_t: t ∈...
We propose two novel conditional gradient-based methods for solving
stru...
Compared to minimization problems, the min-max landscape in machine lear...
We introduce a sampling perspective to tackle the challenging task of
tr...
We reconsider the training objective of Generative Adversarial Networks
...
We generalize the Langevin Dynamics through the mirror descent framework...
Information concentration of probability measures have important implica...
We revisit the problem of solving two-player zero-sum games in the
decen...