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 …

Deep learning has transformed computer vision, natural language processing, and speech
recognition. However, two critical questions remain obscure: 1) why do deep neural …

The ability of machine learning (ML) algorithms to generalize well to unseen data has been
studied through the lens of information theory, by bounding the generalization error with the …

Quantifying the impact of individual data samples on machine learning models is an open
research problem. This is particularly relevant when complex and high-dimensional …

Large Language Models have received significant attention due to their abilities to solve a
wide range of complex tasks. However these models memorize a significant proportion of …

It is well-known that a neural network learning process—along with its connections to fitting,
compression, and generalization—is not yet well understood. In this paper, we propose a …

Deep neural networks complete a feature extraction task by propagating the inputs through
multiple modules. However, how the representations evolve with the gradient-based …

To gain a deeper understanding of the behavior and learning dynamics of artificial neural
networks, mathematical abstractions and models are valuable. They provide a simplified …

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

When deploying deep learning models such as convolutional neural networks (CNNs) in
safety-critical domains, it is important to understand the predictions made by these black-box …