This work presents general upper and lower bounds on the Kullback-Leibler (KL) divergence of coreset approximations that reflect the full range of applicability of Bayesian coresets.

Recently, an insightful phenomenon known as neural collapse (NC) [Papyan et al., 2020] has been

In contextual dynamic pricing, a seller sequentially prices goods based on contextual information.

We study the problem of transfer learning and fine-tuning in linear models for both regression and binary classification. In particular, we consider the use of stochastic gradient descent (SGD) on a linear model initialized with pretrained weights and using a small training data set from the target distribution.

Since deep learning models are usually deployed in non-stationary environments, it is imperative to improve their robustness to out-of-distribution (OOD) data.