Abstract Context Machine Learning (ML) has been at the heart of many innovations over the
past years. However, including it in so-called “safety-critical” systems such as automotive or …

Federated learning aims to learn a global model that performs well on client devices with
limited cross-client communication. Personalized federated learning (PFL) further extends …

Meta-learning can successfully acquire useful inductive biases from data. Yet, its
generalization properties to unseen learning tasks are poorly understood. Particularly if the …

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 …

We propose the first general PAC-Bayesian generalization bounds for adversarial
robustness, that estimate, at test time, how much a model will be invariant to imperceptible …

Gaussian processes provide a framework for nonlinear nonparametric Bayesian inference
widely applicable across science and engineering. Unfortunately, their computational …

Data-driven models analyze power grids under incomplete physical information, and their
accuracy has been mostly validated empirically using certain training and testing datasets …

We investigate a stochastic counterpart of majority votes over finite ensembles of classifiers,
and study its generalization properties. While our approach holds for arbitrary distributions …

PAC-Bayes has recently re-emerged as an effective theory with which one can derive
principled learning algorithms with tight performance guarantees. However, applications of …

Abstract Neural Stochastic Differential Equations model a dynamical environment with
neural nets assigned to their drift and diffusion terms. The high expressive power of their …