Learning Graphical Models
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.
New Complexity-Theoretic Frontiers of Tractability for Neural Network Training
A neural network (cf. Figure 1) can be thought of as a directed acyclic network consisting of
Learning via Wasserstein-Based High Probability Generalisation Bounds
The authors contributed equally to this work 37th Conference on Neural Information Processing Systems (NeurIPS 2023). Developing upper bounds on the generalisation gap, i.e., generalisation bounds has been a longstanding topic in statistical learning.