Pages

Publications

Publications

Journals G. Franzese, S. Rossi, L. Yang, A. Finamore, D. Rossi, M. Filippone, and P. Michiardi. How much is enough? a study on diffusion times in score-based generative models. Entropy, 25(4), 2023. [ link ] 2022 B.-H. Tran, S. Rossi, D. Milios, and M. Filippone. All you need is a good functional prior for Bayesian deep learning. Journal of Machine Learning Research, 23(74):1--56, 2022. [ link ] S. Marmin and M. Filippone. Deep Gaussian Processes for Calibration of Computer Models (with Discussion). Bayesian Analysis, 17(4):1301 -- 1350, 2022. [ link ] C. Carota, M. Filippone, and S. Polettini

Front Page

Bayesian Deep Learning Research Group

Prof Maurizio Filippone leads the Bayesian Deep Learning (BDL) group Keywords: Bayesian Inference, Deep Learning, Gaussian Processes The Bayesian Deep Learning group focuses on the development of flexible and scalable approaches to infer quantities of interest in a variety of statistical modeling scenarios in life and environmental sciences, with the ultimate goal of obtaining a sound quantification of uncertainty to assist decision-making. Please follow the links offered below to find out more about the currently ongoing projects but also about the internship opportunities that exist within

Other

BDL News Archive

21-09-23 The paper "One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models" has been accepted at NeurIPS 2023! ( link) 21-09-23 The paper "Continuous-Time Functional Diffusion Processes" has been accepted at NeurIPS 2023! ( link) 20-09-23 Delighted to be an invited speaker at the GenU workshop in Copenhagen presenting "Bayesian Autoencoders" ( link) 25-07-23 Poster presentation at ICML of our paper "Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes" ( link) 23-07-23 Delighted to be an invited speaker at the AABI workshop at ICML