Publications

Rayen Dhahri, Alexander Immer, Betrand Charpentier, Stephan Günnemann, Vincent Fortuin

January, 2024 arXiv preprint arXiv:2402.15978

Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood

Theodore Papamarkou, Maria Skoularidou, Konstantina Palla, Laurence Aitchison, Julyan Arbel, David Dunson, Maurizio Filippone, Vincent Fortuin, Philipp Hennig, Aliaksandr Hubin, Alexander Immer, Theofanis Karaletsos, Mohammad Emtiyaz Khan, Agustinus Kristiadi, Yingzhen Li, Stephan Mandt, Christopher Nemeth, Michael A Osborne, Tim GJ Rudner, David Rügamer, Yee Whye Teh, Max Welling, Andrew Gordon Wilson, Ruqi Zhang

January, 2024 arXiv preprint arXiv:2402.00809

Position Paper: Bayesian Deep Learning in the Age of Large-Scale AI

Laura Manduchi, Kushagra Pandey, Robert Bamler, Ryan Cotterell, Sina Däubener, Sophie Fellenz, Asja Fischer, Thomas Gärtner, Matthias Kirchler, Marius Kloft, Yingzhen Li, Christoph Lippert, Gerard de Melo, Eric Nalisnick, Björn Ommer, Rajesh Ranganath, Maja Rudolph, Karen Ullrich, Guy Van den Broeck, Julia E Vogt, Yixin Wang, Florian Wenzel, Frank Wood, Stephan Mandt, Vincent Fortuin

January, 2024 arXiv preprint arXiv:2403.00025

On the Challenges and Opportunities in Generative AI

Alexander Möllers, Alexander Immer, Vincent Fortuin, Elvin Isufi

January, 2024 International Conference on Acoustics, Speech, and Signal Processing

Hodge-Aware Contrastive Learning

Eliot Wong-Toi, Alex Boyd, Vincent Fortuin, Stephan Mandt

January, 2023 arXiv preprint arXiv:2306.16717

Understanding pathologies of deep heteroskedastic regression

Alexander Möllers, Alexander Immer, Elvin Isufi, Vincent Fortuin

January, 2023 Fifth Symposium on Advances in Approximate Bayesian Inference

Uncertainty in Graph Contrastive Learning with Bayesian Neural Networks

Jonas Rothfuss, Martin Josifoski, Vincent Fortuin, Andreas Krause

January, 2023 Journal of Machine Learning Research

Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practice

Agustinus Kristiadi, Alexander Immer, Runa Eschenhagen, Vincent Fortuin

January, 2023 Fifth Symposium on Advances in Approximate Bayesian Inference

Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization

Mrinank Sharma, Tom Rainforth, Yee Whye Teh, Vincent Fortuin

January, 2023 arXiv preprint arXiv:2304.01762

Incorporating Unlabelled Data into Bayesian Neural Networks

Kouroche Bouchiat, Alexander Immer, Hugo Yèche, Gunnar Rätsch, Vincent Fortuin

January, 2023 Fifth Symposium on Advances in Approximate Bayesian Inference

Improving Neural Additive Models with Bayesian Principles

Szilvia Ujváry, Gergely Flamich, Vincent Fortuin, José Miguel Hernández Lobato

January, 2023 arXiv preprint arXiv:2310.20053

Estimating optimal PAC-Bayes bounds with Hamiltonian Monte Carlo

Vincent Fortuin, Yingzhen Li, Kevin Murphy, Stephan Mandt, Laura Manduchi

January, 2023 Dagstuhl Reports

Challenges and Perspectives in Deep Generative Modeling (Dagstuhl Seminar 23072)

Julyan Arbel, Konstantinos Pitas, Mariia Vladimirova, Vincent Fortuin

January, 2023 arXiv preprint arXiv:2309.16314

A primer on Bayesian neural networks: review and debates

James Urquhart Allingham, Florian Wenzel, Zelda E Mariet, Basil Mustafa, Joan Puigcerver, Neil Houlsby, Ghassen Jerfel, Vincent Fortuin, Balaji Lakshminarayanan, Jasper Snoek, Dustin Tran, Carlos Riquelme Ruiz, Rodolphe Jenatton

January, 2022 Transactions on Machine Learning Research

Sparse MoEs meet Efficient Ensembles

Noah Berner, Vincent Fortuin, Jonas Landman

January, 2022 Fourth Symposium on Advances in Approximate Bayesian Inference

Quantum Bayesian Neural Networks

Alexander Immer, Lucas Torroba Hennigen, Vincent Fortuin, Ryan Cotterell

January, 2022 Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Probing as quantifying inductive bias

Vincent Fortuin

January, 2022 International Statistical Review

Priors in Bayesian deep learning: A review

Tristan Cinquin, Alexander Immer, Max Horn, Vincent Fortuin

January, 2022 Fourth Symposium on Advances in Approximate Bayesian Inference

Pathologies in Priors and Inference for Bayesian Transformers

Florian Schottmann, Vincent Fortuin, Edoardo Ponti, Ryan Cotterell

January, 2022 Swiss Text Analytics Conference

On Interpretable Reranking-Based Dependency Parsing Systems

Simon Bing, Vincent Fortuin, Gunnar Rätsch

January, 2022 Fourth Symposium on Advances in Approximate Bayesian Inference

On Disentanglement in Gaussian Process Variational Autoencoders

Lauro Langosco di Langosco, Vincent Fortuin, Heiko Strathmann

January, 2022 Fourth Symposium on Advances in Approximate Bayesian Inference

Neural Variational Gradient Descent

Marcello Massimo Negri, Vincent Fortuin, Jan Stuehmer

January, 2022 Fourth Symposium on Advances in Approximate Bayesian Inference

Meta-learning richer priors for VAEs

Alexander Immer, Tycho van der Ouderaa, Gunnar Rätsch, Vincent Fortuin, Mark van der Wilk

January, 2022 Advances in Neural Information Processing Systems

Invariance learning in deep neural networks with differentiable Laplace approximations

Vincent Fortuin, Mark Collier, Florian Wenzel, James Urquhart Allingham, Jeremiah Zhe Liu, Dustin Tran, Balaji Lakshminarayanan, Jesse Berent, Rodolphe Jenatton, Effrosyni Kokiopoulou

January, 2022 Transactions on Machine Learning Research

Deep classifiers with label noise modeling and distance awareness

Seth Nabarro, Stoil Ganev, Adrià Garriga-Alonso, Vincent Fortuin, Mark van der Wilk, Laurence Aitchison

January, 2022 Uncertainty in Artificial Intelligence

Data augmentation in Bayesian neural networks and the cold posterior effect

Vincent Fortuin, Adrià Garriga-Alonso, Sebastian W Ober, Florian Wenzel, Gunnar Rätsch, Richard E Turner, Mark van der Wilk, Laurence Aitchison

January, 2022 International Conference on Learning Representations

Bayesian neural network priors revisited

Laura Manduchi, Matthias Hüser, Martin Faltys, Julia Vogt, Gunnar Rätsch, Vincent Fortuin

January, 2021 Proceedings of the Conference on Health, Inference, and Learning

T-DPSOM: An interpretable clustering method for unsupervised learning of patient health states

Vincent Fortuin, Gideon Dresdner, Heiko Strathmann, Gunnar Rätsch

January, 2021 IEEE Access

Sparse Gaussian processes on discrete domains

Alexander Immer, Matthias Bauer, Vincent Fortuin, Gunnar Rätsch, Mohammad Emtiyaz Khan

January, 2021 International Conference on Machine Learning

Scalable marginal likelihood estimation for model selection in deep learning

Metod Jazbec, Matt Ashman, Vincent Fortuin, Michael Pearce, Stephan Mandt, Gunnar Rätsch

January, 2021 International Conference on Artificial Intelligence and Statistics

Scalable Gaussian process variational autoencoders

Francesco D'Angelo, Vincent Fortuin

January, 2021 Advances in Neural Information Processing Systems

Repulsive deep ensembles are Bayesian

Alexandre Bense, Amir Joudaki, Tim GJ Rudner, Vincent Fortuin

January, 2021 NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications

PCA Subspaces Are Not Always Optimal for Bayesian Learning

Jonas Rothfuss, Vincent Fortuin, Martin Josifoski, Andreas Krause

January, 2021 International Conference on Machine Learning

PACOH: Bayes-optimal meta-learning with PAC-guarantees

Vincent Fortuin

January, 2021

On the Choice of Priors in Bayesian Deep Learning

Francesco D'Angelo, Vincent Fortuin, Florian Wenzel

January, 2021 arXiv preprint arXiv:2106.10760

On Stein variational neural network ensembles

Andreas Kopf, Vincent Fortuin, Vignesh Ram Somnath, Manfred Claassen

January, 2021 PLoS Computational Biology

Mixture-of-Experts Variational Autoencoder for clustering and generating from similarity-based representations on single cell data

Margherita Rosnati, Vincent Fortuin

January, 2021 Plos ONE

MGP-AttTCN: An interpretable machine learning model for the prediction of sepsis

Metod Jazbec, Michael Arthur Leopold Pearce, Vincent Fortuin

January, 2021 Third Symposium on Advances in Approximate Bayesian Inference

Factorized Gaussian Process Variational Autoencoders

Adrià Garriga-Alonso, Vincent Fortuin

January, 2021 Third Symposium on Advances in Approximate Bayesian Inference

Exact Langevin Dynamics with Stochastic Gradients

Vincent Fortuin, Adrià Garriga-Alonso, Mark van der Wilk, Laurence Aitchison

January, 2021 Software Impacts

BNNpriors: A library for Bayesian neural network inference with different prior distributions

Francesco D'Angelo, Vincent Fortuin

January, 2021 Third Symposium on Advances in Approximate Bayesian Inference

Annealed Stein Variational Gradient Descent

Nikolaos Mourdoukoutas, Marco Federici, Georges Pantalos, Mark van der Wilk, Vincent Fortuin

January, 2021 arXiv preprint arXiv:2107.09301

A Bayesian Approach to Invariant Deep Neural Networks

Matthew Ashman, Jonathan So, Will Tebbutt, Vincent Fortuin, Michael Pearce, Richard E Turner

January, 2020 arXiv preprint arXiv:2010.10177

Sparse Gaussian process variational autoencoders

Vincent Fortuin, Dmitry Baranchuk, Gunnar Rätsch, Stephan Mandt

January, 2020 International Conference on Artificial Intelligence and Statistics

GP-VAE: Deep probabilistic time series imputation

Kamil Ciosek, Vincent Fortuin, Ryota Tomioka, Katja Hofmann, Richard Turner

January, 2020 International Conference on Learning Representations

Conservative uncertainty estimation by fitting prior networks

Vincent Fortuin, Matthias Hüser, Francesco Locatello, Heiko Strathmann, Gunnar Rätsch

January, 2019 International Conference on Learning Representations

SOM-VAE: Interpretable discrete representation learning on time series

Andreas Georgiou, Vincent Fortuin, Harun Mustafa, Gunnar Rätsch

January, 2019 arXiv preprint arXiv:1909.13146

META$^2$: Memory-efficient taxonomic classification and abundance estimation for metagenomics with deep learning

Vincent Fortuin, Heiko Strathmann, Gunnar Rätsch

January, 2019 arXiv preprint arXiv:1901.08098

Meta-learning mean functions for Gaussian processes

Laura Manduchi, Matthias Hüser, Julia Vogt, Gunnar Rätsch, Vincent Fortuin

January, 2019 arXiv preprint arXiv:1910.01590

DPSOM: Deep probabilistic clustering with self-organizing maps

Stefan Ganscha, Vincent Fortuin, Max Horn, Eirini Arvaniti, Manfred Claassen

January, 2018 bioRxiv

Supervised learning on synthetic data for reverse engineering gene regulatory networks from experimental time-series

Tim GJ Rudner, Vincent Fortuin, Yee Whye Teh, Yarin Gal

January, 2018 Workshop on Bayesian Deep Learning, NeurIPS

On the connection between neural processes and Gaussian processes with deep kernels

Vincent Fortuin, Romann Weber, Sasha Schriber, Diana Wotruba, Markus Gross

January, 2018 Proceedings of the AAAI Conference on Artificial Intelligence

InspireMe: learning sequence models for stories