Any well-behaved generative model over a variable $\mathbf {x} $ can be expressed as a
deterministic transformation of an exogenous ('outsourced') Gaussian noise variable …

Sampling from unnormalized target distributions is a fundamental yet challenging task in
machine learning and statistics. Existing sampling algorithms typically require many iterative …

Given an unnormalized probability density $\pi\propto\mathrm {e}^{-V} $, estimating its
normalizing constant $ Z=\int_ {\mathbb {R}^ d}\mathrm {e}^{-V (x)}\mathrm {d} x $ or free …

Maximum entropy reinforcement learning (MaxEnt-RL) has become the standard approach
to RL due to its beneficial exploration properties. Traditionally, policies are parameterized …