Despite the existence of many applied scenarios where the relationship between a pair changes, change point methods specifically designed for paired data are quite scarce.

In this work, we demonstrate the restrictiveness of these assumptions using three canonical models in machine learning.

We include some additional preliminary background information.

Stochastic gradient descent (SGD) is a pillar of modern machine learning, serving as the go-to optimization algorithm for a diverse array of problems. While the empirical success of SGD is often attributed to its computational efficiency and favorable generalization behavior, neither effect is well understood and disentangling them remains an open problem.

Our approach relies on an accelerated method that queries a ball optimization oracle, i.e., a subroutine that minimizes the objective within a small ball around the query point. Our main contribution is efficient implementations of this oracle for DRO objectives.