Publications

Rayen Dhahri, Alexander Immer, Betrand Charpentier, Stephan Günnemann, Vincent Fortuin (2024). Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood. arXiv preprint arXiv:2402.15978.

Cite URL

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 (2024). Position Paper: Bayesian Deep Learning in the Age of Large-Scale AI. arXiv preprint arXiv:2402.00809.

Cite URL

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 (2024). On the Challenges and Opportunities in Generative AI. arXiv preprint arXiv:2403.00025.

Cite URL

Alexander Möllers, Alexander Immer, Vincent Fortuin, Elvin Isufi (2024). Hodge-Aware Contrastive Learning. International Conference on Acoustics, Speech, and Signal Processing.

Cite URL

Eliot Wong-Toi, Alex Boyd, Vincent Fortuin, Stephan Mandt (2023). Understanding pathologies of deep heteroskedastic regression. arXiv preprint arXiv:2306.16717.

Cite URL

Alexander Möllers, Alexander Immer, Elvin Isufi, Vincent Fortuin (2023). Uncertainty in Graph Contrastive Learning with Bayesian Neural Networks. Fifth Symposium on Advances in Approximate Bayesian Inference.

Cite URL

Jonas Rothfuss, Martin Josifoski, Vincent Fortuin, Andreas Krause (2023). Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practice. Journal of Machine Learning Research.

Cite URL

Agustinus Kristiadi, Alexander Immer, Runa Eschenhagen, Vincent Fortuin (2023). Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization. Fifth Symposium on Advances in Approximate Bayesian Inference.

Cite URL

Mrinank Sharma, Tom Rainforth, Yee Whye Teh, Vincent Fortuin (2023). Incorporating Unlabelled Data into Bayesian Neural Networks. arXiv preprint arXiv:2304.01762.

Cite URL

Kouroche Bouchiat, Alexander Immer, Hugo Yèche, Gunnar Rätsch, Vincent Fortuin (2023). Improving Neural Additive Models with Bayesian Principles. Fifth Symposium on Advances in Approximate Bayesian Inference.

Cite URL

Szilvia Ujváry, Gergely Flamich, Vincent Fortuin, José Miguel Hernández Lobato (2023). Estimating optimal PAC-Bayes bounds with Hamiltonian Monte Carlo. arXiv preprint arXiv:2310.20053.

Cite URL

Vincent Fortuin, Yingzhen Li, Kevin Murphy, Stephan Mandt, Laura Manduchi (2023). Challenges and Perspectives in Deep Generative Modeling (Dagstuhl Seminar 23072). Dagstuhl Reports.

Cite DOI URL

Julyan Arbel, Konstantinos Pitas, Mariia Vladimirova, Vincent Fortuin (2023). A primer on Bayesian neural networks: review and debates. arXiv preprint arXiv:2309.16314.

Cite URL

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 (2022). Sparse MoEs meet Efficient Ensembles. Transactions on Machine Learning Research.

Cite URL

Noah Berner, Vincent Fortuin, Jonas Landman (2022). Quantum Bayesian Neural Networks. Fourth Symposium on Advances in Approximate Bayesian Inference.

Cite URL

Alexander Immer, Lucas Torroba Hennigen, Vincent Fortuin, Ryan Cotterell (2022). Probing as quantifying inductive bias. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

Cite URL

Vincent Fortuin (2022). Priors in Bayesian deep learning: A review. International Statistical Review.

Cite URL

Tristan Cinquin, Alexander Immer, Max Horn, Vincent Fortuin (2022). Pathologies in Priors and Inference for Bayesian Transformers. Fourth Symposium on Advances in Approximate Bayesian Inference.

Cite URL

Florian Schottmann, Vincent Fortuin, Edoardo Ponti, Ryan Cotterell (2022). On Interpretable Reranking-Based Dependency Parsing Systems. Swiss Text Analytics Conference.

PDF Cite

Simon Bing, Vincent Fortuin, Gunnar Rätsch (2022). On Disentanglement in Gaussian Process Variational Autoencoders. Fourth Symposium on Advances in Approximate Bayesian Inference.

Cite URL

Lauro Langosco di Langosco, Vincent Fortuin, Heiko Strathmann (2022). Neural Variational Gradient Descent. Fourth Symposium on Advances in Approximate Bayesian Inference.

Cite URL

Marcello Massimo Negri, Vincent Fortuin, Jan Stuehmer (2022). Meta-learning richer priors for VAEs. Fourth Symposium on Advances in Approximate Bayesian Inference.

Cite URL

Alexander Immer, Tycho van der Ouderaa, Gunnar Rätsch, Vincent Fortuin, Mark van der Wilk (2022). Invariance learning in deep neural networks with differentiable Laplace approximations. Advances in Neural Information Processing Systems.

Cite URL

Vincent Fortuin, Mark Collier, Florian Wenzel, James Urquhart Allingham, Jeremiah Zhe Liu, Dustin Tran, Balaji Lakshminarayanan, Jesse Berent, Rodolphe Jenatton, Effrosyni Kokiopoulou (2022). Deep classifiers with label noise modeling and distance awareness. Transactions on Machine Learning Research.

Cite URL

Seth Nabarro, Stoil Ganev, Adrià Garriga-Alonso, Vincent Fortuin, Mark van der Wilk, Laurence Aitchison (2022). Data augmentation in Bayesian neural networks and the cold posterior effect. Uncertainty in Artificial Intelligence.

Cite URL

Vincent Fortuin, Adrià Garriga-Alonso, Sebastian W Ober, Florian Wenzel, Gunnar Rätsch, Richard E Turner, Mark van der Wilk, Laurence Aitchison (2022). Bayesian neural network priors revisited. International Conference on Learning Representations.

Cite URL

Laura Manduchi, Matthias Hüser, Martin Faltys, Julia Vogt, Gunnar Rätsch, Vincent Fortuin (2021). T-DPSOM: An interpretable clustering method for unsupervised learning of patient health states. Proceedings of the Conference on Health, Inference, and Learning.

Cite URL

Vincent Fortuin, Gideon Dresdner, Heiko Strathmann, Gunnar Rätsch (2021). Sparse Gaussian processes on discrete domains. IEEE Access.

Cite URL

Alexander Immer, Matthias Bauer, Vincent Fortuin, Gunnar Rätsch, Mohammad Emtiyaz Khan (2021). Scalable marginal likelihood estimation for model selection in deep learning. International Conference on Machine Learning.

Cite URL

Metod Jazbec, Matt Ashman, Vincent Fortuin, Michael Pearce, Stephan Mandt, Gunnar Rätsch (2021). Scalable Gaussian process variational autoencoders. International Conference on Artificial Intelligence and Statistics.

Cite URL

Francesco D'Angelo, Vincent Fortuin (2021). Repulsive deep ensembles are Bayesian. Advances in Neural Information Processing Systems.

Cite URL

Alexandre Bense, Amir Joudaki, Tim GJ Rudner, Vincent Fortuin (2021). PCA Subspaces Are Not Always Optimal for Bayesian Learning. NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications.

Cite URL

Jonas Rothfuss, Vincent Fortuin, Martin Josifoski, Andreas Krause (2021). PACOH: Bayes-optimal meta-learning with PAC-guarantees. International Conference on Machine Learning.

Cite URL

Vincent Fortuin (2021). On the Choice of Priors in Bayesian Deep Learning.

Cite URL

Francesco D'Angelo, Vincent Fortuin, Florian Wenzel (2021). On Stein variational neural network ensembles. arXiv preprint arXiv:2106.10760.

Cite URL

Andreas Kopf, Vincent Fortuin, Vignesh Ram Somnath, Manfred Claassen (2021). Mixture-of-Experts Variational Autoencoder for clustering and generating from similarity-based representations on single cell data. PLoS Computational Biology.

Cite URL

Margherita Rosnati, Vincent Fortuin (2021). MGP-AttTCN: An interpretable machine learning model for the prediction of sepsis. Plos ONE.

Cite URL

Metod Jazbec, Michael Arthur Leopold Pearce, Vincent Fortuin (2021). Factorized Gaussian Process Variational Autoencoders. Third Symposium on Advances in Approximate Bayesian Inference.

Cite URL

Adrià Garriga-Alonso, Vincent Fortuin (2021). Exact Langevin Dynamics with Stochastic Gradients. Third Symposium on Advances in Approximate Bayesian Inference.

Cite URL

Vincent Fortuin, Adrià Garriga-Alonso, Mark van der Wilk, Laurence Aitchison (2021). BNNpriors: A library for Bayesian neural network inference with different prior distributions. Software Impacts.

Cite URL

Francesco D'Angelo, Vincent Fortuin (2021). Annealed Stein Variational Gradient Descent. Third Symposium on Advances in Approximate Bayesian Inference.

Cite URL

Nikolaos Mourdoukoutas, Marco Federici, Georges Pantalos, Mark van der Wilk, Vincent Fortuin (2021). A Bayesian Approach to Invariant Deep Neural Networks. arXiv preprint arXiv:2107.09301.

Cite URL

Matthew Ashman, Jonathan So, Will Tebbutt, Vincent Fortuin, Michael Pearce, Richard E Turner (2020). Sparse Gaussian process variational autoencoders. arXiv preprint arXiv:2010.10177.

Cite URL

Vincent Fortuin, Dmitry Baranchuk, Gunnar Rätsch, Stephan Mandt (2020). GP-VAE: Deep probabilistic time series imputation. International Conference on Artificial Intelligence and Statistics.

Cite URL

Kamil Ciosek, Vincent Fortuin, Ryota Tomioka, Katja Hofmann, Richard Turner (2020). Conservative uncertainty estimation by fitting prior networks. International Conference on Learning Representations.

Cite URL

Vincent Fortuin, Matthias Hüser, Francesco Locatello, Heiko Strathmann, Gunnar Rätsch (2019). SOM-VAE: Interpretable discrete representation learning on time series. International Conference on Learning Representations.

Cite URL

Andreas Georgiou, Vincent Fortuin, Harun Mustafa, Gunnar Rätsch (2019). META$^2$: Memory-efficient taxonomic classification and abundance estimation for metagenomics with deep learning. arXiv preprint arXiv:1909.13146.

Cite URL

Vincent Fortuin, Heiko Strathmann, Gunnar Rätsch (2019). Meta-learning mean functions for Gaussian processes. arXiv preprint arXiv:1901.08098.

Cite URL

Laura Manduchi, Matthias Hüser, Julia Vogt, Gunnar Rätsch, Vincent Fortuin (2019). DPSOM: Deep probabilistic clustering with self-organizing maps. arXiv preprint arXiv:1910.01590.

Cite URL

Stefan Ganscha, Vincent Fortuin, Max Horn, Eirini Arvaniti, Manfred Claassen (2018). Supervised learning on synthetic data for reverse engineering gene regulatory networks from experimental time-series. bioRxiv.

Cite URL

Tim GJ Rudner, Vincent Fortuin, Yee Whye Teh, Yarin Gal (2018). On the connection between neural processes and Gaussian processes with deep kernels. Workshop on Bayesian Deep Learning, NeurIPS.

PDF Cite

Vincent Fortuin, Romann Weber, Sasha Schriber, Diana Wotruba, Markus Gross (2018). InspireMe: learning sequence models for stories. Proceedings of the AAAI Conference on Artificial Intelligence.

Cite URL