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 …

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 …

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 …

Bernstein's condition is a key assumption that guarantees fast rates in machine learning. For
example, the Gibbs algorithm with prior $\pi $ has an excess risk in $ O (d_ {\pi}/n) $, as …

We provide a new information-theoretic generalization error bound that is exactly tight (ie,
matching even the constant) for the canonical quadratic Gaussian (location) problem. Most …

Meta learning has attracted much attention recently in machine learning community.
Contrary to conventional machine learning aiming to learn inherent prediction rules to …

We analyze the generalization ability of joint-training meta learning algorithms via the Gibbs
algorithm. Our exact characterization of the expected meta generalization error for the meta …

We introduce a new framework for studying meta-learning methods using PAC-Bayesian
theory. Its main advantage over previous work is that it allows for more flexibility in how the …

There remains a list of unanswered research questions on deep learning (DL), including the
remarkable generalization power of overparametrized neural networks, the efficient …

In recent years, information-theoretic generalization bounds have emerged as a promising
approach for analyzing the generalization capabilities of meta-learning algorithms …