A fundamental question in theoretical machine learning is generalization. Over the past
decades, the PAC-Bayesian approach has been established as a flexible framework to …

We study the generalization properties of the popular stochastic optimization method known
as stochastic gradient descent (SGD) for optimizing general non-convex loss functions. Our …

We derive information-theoretic generalization bounds for supervised learning algorithms
based on the information contained in predictions rather than in the output of the training …

We present a new family of information-theoretic generalization bounds, in which the
training loss and the population loss are compared through a jointly convex function. This …

In this work, we investigate the expressiveness of the" conditional mutual information"(CMI)
framework of Steinke and Zakynthinou (2020) and the prospect of using it to provide a …

This work presents several expected generalization error bounds based on the Wasserstein
distance. More specifically, it introduces full-dataset, single-letter, and random-subset …

In this work, we investigate the interplay between memorization and learning in the context
of\emph {stochastic convex optimization}(SCO). We define memorization via the information …

In this work, we present a variety of novel information-theoretic generalization bounds for
learning algorithms, from the supersample setting of Steinke & Zakynthinou (2020)-the …

To date, no “information-theoretic” frameworks for reasoning about generalization error have
been shown to establish minimax rates for gradient descent in the setting of stochastic …

We propose an information-theoretic bound on the generalization error based on a
combination of the error decomposition technique of Bu et al. and the conditional mutual …