Achieving such guarantees generally requires the injection of noise, either directly into parameter estimates or into the estimation process.

In many scientific applications, we observe a system in different conditions in which its components may change, rather than in isolation.

In variational inference, the benefits of Bayesian models rely on accurately capturing the true posterior distribution. We propose using neural samplers that specify implicit distributions, which are well-suited for approximating complex multimodal and correlated posteriors in high-dimensional spaces.

Regularization is one of the most fundamental topics in optimization, statistics and machine learning.