Publications

Tristan Cinquin, Stanley Lo, Felix Strieth-Kalthoff, Alan Aspuru-Guzik, Geoff Pleiss, Robert Bamler, Tim GJ Rudner, Vincent Fortuin, Agustinus Kristiadi (2025). What Actually Matters for Materials Discovery: Pitfalls and Recommendations in Bayesian Optimization. Seventh Symposium on Advances in Approximate Bayesian Inference.

James Odgers, Ruby Sedgwick, Chrysoula Kappatou, Ruth Misener, Sarah Filippi (2025). Weighted-Sum of Gaussian Process Latent Variable Models.

Tommy Rochussen, Vincent Fortuin (2025). Sparse Gaussian Neural Processes. Proceedings of the Symposium on Advances in Approximate Bayesian Inference.

Vincent Fortuin, Mohammad Emtiyaz Khan, Mark van der Wilk, Zoubin Ghahramani, Katharine Fisher (2025). Rethinking the Role of Bayesianism in the Age of Modern AI (Dagstuhl Seminar 24461). Dagstuhl Reports.

Annika Schneider, Gaurav Khemka, David Pitt, Jinhui Zhang (2025). Quantifying and hedging economic risk in disability income insurance portfolios. Annals of Actuarial Science.

Michal Kmicikiewicz, Vincent Fortuin, Ewa Szczurek (2025). ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods. Advances in Neural Information Processing Systems.

Klemens Flöge, Srisruthi Udayakumar, Johanna Sommer, Marie Piraud, Stefan Kesselheim, Vincent Fortuin, Stephan Günnemann, Karel J van der Weg, Holger Gohlke, Erinc Merdivan, Alina Bazarova (2025). OneProt: Towards multi-modal protein foundation models via latent space alignment of sequence, structure, binding sites and text encoders. PLoS Computational Biology.

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 (2025). On the Challenges and Opportunities in Generative AI. Transactions on Machine Learning Research.

Annika Schneider, Lukas Schüttler, Jan Marco Ruiz de Vargas, Michael Eichelbeck, Christoph Goebel (2025). e-SparX: A Graph-Based Artifact Exchange Platform to Accelerate Machine Learning Research in the Energy Systems Community. Proceedings of the 16th ACM International Conference on Future and Sustainable Energy Systems.

Fedor Sergeev, Manuel Burger, Polina Leshetkina, Vincent Fortuin, Gunnar Rätsch, Rita Kuznetsova (2025). Data-Driven Discovery of Feature Groups in Clinical Time Series. Machine Learning for Health Symposium.

Jan Marco Ruiz de Vargas, Annika Schneider, Pierre Pinson, Christoph Goebel (2025). Data Sharing between Wind Energy Producers: Economic Incentives and Strategic Behavior. Proceedings of the 16th ACM International Conference on Future and Sustainable Energy Systems.

Arik Reuter, Tim GJ Rudner, Vincent Fortuin, David Rügamer (2025). Can Transformers Learn Full Bayesian Inference in Context?. International Conference on Machine Learning.

Sylvie Delacroix, Diana Robinson, Umang Bhatt, Jacopo Domenicucci, Jessica Montgomery, Gaël Varoquaux, Carl Henrik Ek, Vincent Fortuin, Yulan He, Tom Diethe, Neill Campbell, El-Assady Mennatallah, Søren Hauberg, Ivana Dusparic, Neil D Lawrence (2025). Beyond quantification: Navigating uncertainty in professional AI systems. RSS: Data Science and Artificial Intelligence.

Eliot Wong-Toi, Alex Boyd, Vincent Fortuin, Stephan Mandt (2024). Understanding pathologies of deep heteroskedastic regression. Uncertainty in Artificial Intelligence.

Fedor Sergeev, Paola Malsot, Gunnar Rätsch, Vincent Fortuin (2024). Towards Dynamic Feature Acquisition on Medical Time Series by Maximizing Conditional Mutual Information. ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling.

Tommy Rochussen (2024). Structured Partial Stochasticity in Bayesian Neural Networks. Sixth Symposium on Advances in Approximate Bayesian Inference - Non Archival Track.

Klemens Flöge, Muhammad Abdul Moeed, Vincent Fortuin (2024). Stein Variational Newton Neural Network Ensembles. ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling.

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. Advances in Neural Information Processing Systems.

Jose E. Sanchez-Lopez, Javier Solís-García, Jose C. Riquelme (2024). Semi-real-time decision tree ensemble algorithms for very short-term solar irradiance forecasting. International Journal of Electrical Power and Energy Systems.

Ben Riegler, James AC Odgers, Vincent Fortuin (2024). Rethinking Exploration in Asynchronous Bayesian Optimization: Standard Acquisition is All You Need. ICML 2025 Workshop on Exploration in AI Today.

Richard D Paul, Alessio Quercia, Vincent Fortuin, Katharina Nöh, Hanno Scharr (2024). Parameter-efficient Bayesian Neural Networks for Uncertainty-aware Depth Estimation. arXiv preprint arXiv:2409.17085.

Mrinank Sharma, Tom Rainforth, Yee Whye Teh, Vincent Fortuin (2024). Incorporating Unlabelled Data into Bayesian Neural Networks. Transactions on Machine Learning Research.

Kouroche Bouchiat, Alexander Immer, Hugo Yèche, Gunnar Rätsch, Vincent Fortuin (2024). Improving Neural Additive Models with Bayesian Principles. International Conference on Machine Learning.

Agustinus Kristiadi, Felix Strieth-Kalthoff, Sriram Ganapathi Subramanian, Vincent Fortuin, Pascal Poupart, Geoff Pleiss (2024). How Useful is Intermittent, Asynchronous Expert Feedback for Bayesian Optimization?. Sixth Symposium on Advances in Approximate Bayesian Inference.

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

Emre Onal, Klemens Flöge, Emma Caldwell, Arsen Sheverdin, Vincent Fortuin (2024). Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models. Sixth Symposium on Advances in Approximate Bayesian Inference.

Tristan Cinquin, Marvin Pförtner, Vincent Fortuin, Philipp Hennig, Robert Bamler (2024). FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning. Advances in Neural Information Processing Systems.

Lena Zellinger, Andreas Stephan, Benjamin Roth (2024). Counterfactual Reasoning with Knowledge Graph Embeddings. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers).

Kseniya Petrova, Maksym Tretiakov, Aleksandr Kotov, Anne H. Monsoro-Burq, Leonid Peshkin (2024). A revised single-cell transcriptomic atlas of Xenopus embryo reveals new differentiation dynamics. bioRxiv preprint.

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.

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.

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.

James Odgers, Chrysoula Kappatou, Ruth Misener, Salvador Garcı́a Muñoz, Sarah Filippi (2023). Probabilistic predictions for partial least squares using bootstrap. AIChE Journal.

Anastasiia Sedova, Lena Zellinger, Benjamin Roth (2023). Learning with noisy labels by adaptive gradient-based outlier removal. Joint European Conference on Machine Learning and Knowledge Discovery in Databases.

Szilvia Ujváry, Gergely Flamich, Vincent Fortuin, José Miguel Hernández Lobato (2023). Estimating optimal PAC-Bayes bounds with Hamiltonian Monte Carlo. NeurIPS 2023 Workshop on Mathematics of Modern Machine Learning.

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

Matthew Ashman, Tommy Rochussen, Adrian Weller (2023). Amortised Inference in Neural Networks for Small-Scale Probabilistic Meta-Learning. Fifth Symposium on Advances in Approximate Bayesian Inference.

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

Zhenisbek Assylbekov, Sultan Nurmukhamedov, Arsen Sheverdin, Thomas Mach (2022). From Hyperbolic Geometry Back to Word Embeddings. Proceedings of the 7th Workshop on Representation Learning for NLP.

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.

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

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).

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

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.

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

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

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

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

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.

Oren Sultan, Rayen Dhahri, Yauheni Mardan, Tobias Eder, Georg Groh (2022). From Judgement's Premises Towards Key Points.

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.

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.

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.

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.

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

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.

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.

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

Arsen Sheverdin, Noud Corten, Alko Knijff, Georg Lange (2021). Reproducibility report for ''Interpretable Complex-Valued Neural Networks for Privacy Protection''. ML Reproducibility Challenge 2020.

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.

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

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

Francesco D'Angelo, Vincent Fortuin, Florian Wenzel (2021). On Stein variational neural network ensembles. ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning.

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.

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

Fedor Sergeev, Nikita Jain, Ivan Knunyants, George Kostenkov, Ekaterina Trofimova (2021). Fast simulation of the LHCb electromagnetic calorimeter response using VAEs and GANs. Journal of Physics: Conference Series.

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

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

Igor B Petrov, Maksim V Muratov, Fedor I Sergeev (2021). Elastic wave propagation modeling during exploratory drilling on artificial ice island. Applied Mathematics and Computational Mechanics for Smart Applications: Proceedings of AMMAI 2020.

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.

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

Nikolaos Mourdoukoutas, Marco Federici, Georges Pantalos, Mark van der Wilk, Vincent Fortuin (2021). A Bayesian Approach to Invariant Deep Neural Networks. ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning.

Arsen Sheverdin, Francesco Monticone, Constantinos Valagiannopoulos (2020). Photonic Inverse Design with Neural Networks: The Case of Invisibility in the Visible. Phys. Rev. Appl..

Igor Borisovich Petrov, Maksim Viktorovich Muratov, Fedor Igorevich Sergeev (2020). Stability analysis of artificial ice islands by methods of mathematical modeling. Doklady Mathematics.

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

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

D Beznosko, K Yelshibekov, R U Beisembaev, E A Beisembaeva, T Beremkulov, A Iakovlev, S Jakupov, A Sheverdin, Z Tagay, T Uakhitov, M I Vildanova, V V Zhukov (2020). Extensive air showers event reconstruction using spatial and temporary particle distribution at Horizon-T experiment. Journal of Physics: Conference Series.

Fedor Sergeev, Elena Bratkovskaya, Ivan Kisel, Iouri Vassiliev (2020). Deep learning for quark--gluon plasma detection in the CBM experiment. International Journal of Modern Physics A.

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

Arsen Sheverdin, Constantinos Valagiannopoulos (2019). Core-shell nanospheres under visible light: Optimal absorption, scattering, and cloaking. Phys. Rev. B.

Stefan Ganscha, Vincent Fortuin, Max Horn, Eirini Arvaniti, Manfred Claassen (2019). Supervised learning on synthetic data for reverse engineering gene regulatory networks from experimental time-series. NeurIPS 2019 Workshop on Machine Learning in Computational Biology.

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.

Andreas Georgiou, Vincent Fortuin, Harun Mustafa, Gunnar Rätsch (2019). META$^2$: Memory-efficient taxonomic classification and abundance estimation for metagenomics with deep learning. NeurIPS 2019 Workshop on Machine Learning in Computational Biology.

Vincent Fortuin, Heiko Strathmann, Gunnar Rätsch (2019). Meta-learning mean functions for Gaussian processes. NeurIPS 2019 Workshop on Bayesian Deep Learning.

Constantinos Valagiannopoulos, Arsen Sheverdin, Adilkhan Sarsen, Aivar Abrashuly (2019). Maximizing Photonic Response with Simple Resonating Structures in Various Geometries. APS March Meeting Abstracts.

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

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.

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

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.