Learning Graphical Models
The Waymo Open Sim Agents Challenge
Simulation agents are controlled objects that perform realistic behaviors in a virtual world.
Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback
In this work, we study the low-rank MDPs with adversarially changed losses in the full-information feedback setting.
Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback
In this work, we study the low-rank MDPs with adversarially changed losses in the full-information feedback setting.
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.
Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection Yu Bai
Building on these "base" ICL algorithms, intriguingly, we show that transformers
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.
A Bayesian Take on Gaussian Process Networks
In the absence of full prior knowledge of the underlying graph, inference on the structure is necessary.