Uncertainty
Distributionally Robust Skeleton Learning of Discrete Bayesian Networks Y eshu Li
The DAG structure of a Bayesian network is typically unknown in practice [Natori et al., 2017,
Causal normalizing flows: from theory to practice
Our focus in this paper is to solve causal inference problems using only observational data and (potentially partial) knowledge on the causal graph of the underlying structural causal model (SCM).
Conditional independence testing under misspecified inductive biases
Then, we study the performance of regression-based CI tests under misspecified inductive biases.
On the Properties of Kullback-Leibler Divergence Between Multivariate Gaussian Distributions
Kullback-Leibler (KL) divergence is one of the most important measures to calculate the difference between probability distributions. In this paper, we theoretically study several properties of KL divergence between multivariate Gaussian distributions.
Switching Autoregressive Low-rank Tensor Models
An important problem in time-series analysis is modeling systems with time-varying dynamics.
Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory
Since their inception, V ariational Autoencoders (V AEs) have become central in machine learning. Despite their widespread use, numerous questions regarding their theoretical properties remain open.