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 …

Compared to traditional machine learning, deep learning can learn deeper abstract data
representation and understand scattered data properties. It has gained considerable …

Abstract Models trained on one set of domains often suffer performance drops on unseen
domains, eg, when wildlife monitoring models are deployed in new camera locations. In this …

We derive a novel information-theoretic analysis of the generalization property of meta-
learning algorithms. Concretely, our analysis proposes a generic understanding in both the …

Deep learning has achieved remarkable success in many machine learning tasks such as
image classification, speech recognition, and game playing. However, these breakthroughs …

Meta-Learning aims to speed up the learning process on new tasks by acquiring useful
inductive biases from datasets of related learning tasks. While, in practice, the number of …

Meta learning has demonstrated tremendous success in few-shot learning with limited
supervised data. In those settings, the meta model is usually overparameterized. While the …

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 …

Recent years have witnessed growing interest in the application of deep neural networks
(DNNs) for receiver design, which can potentially be applied in complex environments …

Recent work has established that the conditional mutual information (CMI) framework of
Steinke and Zakynthinou (2020) is expressive enough to capture generalization guarantees …