activity
20222024
most citedVariational Inference of overparameterized Bayesian Neural Networks: a theoretical and empirical study

2 citations · 2 across the 5 of their papers we have counts for

collaborators

5 papers

stat.ML2024

A Practical Diffusion Path for Sampling

Omar Chehab, Anna Korba

Diffusion models are state-of-the-art methods in generative modeling when samples from a target probability distribution are available, and can be efficiently sampled, using score…

stat.ML2024

Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians

Tom Huix, Anna Korba, Alain Durmus +1

Variational inference (VI) is a popular approach in Bayesian inference, that looks for the best approximation of the posterior distribution within a parametric family, minimizing a…

cs.LG2024

Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Sampling

Imad Aouali, Victor-Emmanuel Brunel, David Rohde +1

Off-policy learning (OPL) often involves minimizing a risk estimator based on importance weighting to correct bias from the logging policy used to collect data. However, this metho…

cs.LG2023

Exponential Smoothing for Off-Policy Learning

Imad Aouali, Victor-Emmanuel Brunel, David Rohde +1

Off-policy learning (OPL) aims at finding improved policies from logged bandit data, often by minimizing the inverse propensity scoring (IPS) estimator of the risk. In this work, w…

stat.ML20222 cited

Variational Inference of overparameterized Bayesian Neural Networks: a theoretical and empirical study

Tom Huix, Szymon Majewski, Alain Durmus +2

This paper studies the Variational Inference (VI) used for training Bayesian Neural Networks (BNN) in the overparameterized regime, i.e., when the number of neurons tends to infini…