Credits: Mike Mackenzie

Papers of the AI4Science Lab

Here we list all scientific research from collaborations with members of the AI4Science Lab: Books and lecture notes, Publications and Preprints.

Books and Lecture Notes

  • Maurice Weiler, Patrick Forré, Erik Verlinde, Max Welling, Equivariant and Coordinate Independent Convolutional Networks - A Gauge Field Theory of Neural Networks, book, 524 pages, 2023.
  • Patrick Forré, Joris M. Mooij, A Mathematical Introduction to Causality, lecture notes, 324 pages, 2023.

Publications

  • Leon Lang, Pierre Baudot, Rick Quax, Patrick Forré, Information Decomposition Diagrams Applied beyond Shannon Entropy: A Generalization of Hu’s Theorem, https://arxiv.org/abs/2202.09393, accepted for Compositionality 6 (23), 2024.
  • Leon Lang, Davis Foote, Stuart Russell, Anca Dragan, Erik Jenner, Scott Emmons, When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback, https://arxiv.org/abs/2402.17747, accepted for NeurIPS 2024.
  • Teodora Pandeva, Martijs Jonker, Leendert Hamoen, Joris Mooij, Patrick Forré, Robust Multi-view Co-expression Network Inference, https://arxiv.org/abs/2409.19991, accepted for NeurIPS 2024 Workshop: Causal Representation Learning.
  • Benjamin Kurt Miller, Ricky T.Q. Chen, Anuroop Sriram, Brandon Wood, FlowMM: Generating Materials with Riemannian Flow Matching, https://arxiv.org/abs/2406.04713, ICML 2024.
  • David Ruhe, Patrick Forré, SINR: Equivariant Neural Vector Fields, openreview, ICML 2024 Workshop: Geometry-grounded Representation Learning and Generative Modeling.
  • Cong Liu, David Ruhe, Patrick Forré, Multivector Neurons: Better and Faster O(n)-Equivariant Clifford Graph Neural Networks, https://arxiv.org/abs/2406.04052, openreview, ICML 2024 Workshop: Geometry-grounded Representation Learning and Generative Modeling.
  • Fiona Lippert, Bart Kranstauber, Patrick Forré, Emiel van Loon, Towards detailed and interpretable hybrid modeling of continental-scale bird migration, openreview, ICML 2024 Workshop: AI4Science.
  • Maksim Zhdanov, David Ruhe, Maurice Weiler, Ana Lucic, Johannes Brandstetter, Patrick Forré, Clifford-Steerable Convolutional Neural Networks, https://arxiv.org/abs/2402.14730, openreview, ICML 2024.
  • Metod Jazbec, Patrick Forré, Stephan Mandt, Dan Zhang, Eric Nalisnick, Early-Exit Neural Networks with Nested Prediction Sets, https://arxiv.org/abs/2311.05931, openreview, UAI 2024
  • Jim Boelrijk, Stef R.A. Molenaar, Tijmen S. Bos, Tina A. Dahlseid, Bernd Ensing, Dwight R. Stoll, Patrick Forré, Bob W.J. Pirok, Enhancing LC x LC separations through Multi-Task Bayesian Optimization, ChemRxiv, https://doi.org/10.1016/j.chroma.2024.464941, J. Chromatogr. A, 1726 (464941), 2024.
  • Teodora Pandeva, Patrick Forré, Aaditya Ramdas, Shubhanshu Shekhar, Deep anytime-valid hypothesis testing, https://arxiv.org/abs/2310.19384, paper, AISTATS 2024, PMLR 238:622-630, 2024.
  • Teodora Pandeva, Tim Bakker, Christian A. Naesseth, Patrick Forré, E-Valuating Classifier Two-Sample Tests, https://arxiv.org/abs/2210.13027, openreview, TMLR 2024.
  • Marco Federici, Patrick Forré, Ryota Tomioka, Bastiaan S. Veeling, Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck, https://arxiv.org/abs/2309.07200, openreview, ICLR 2024.
  • Cong Liu, David Ruhe, Floor Eijkelboom, Patrick Forré, Clifford Group Equivariant Simplicial Message Passing Networks, https://arxiv.org/abs/2402.10011, openreview, ICLR 2024.
  • Mircea Mironenco, Patrick Forré, Lie Group Decompositions for Equivariant Neural Networks, https://arxiv.org/abs/2310.11366, openreview, ICLR 2024.
  • Maximilian Lipp, Wei Li, Ksenia Abrashitova, Patrick Forré, Lyuba Amitonova, Lightweight super-resolution multimode fiber imaging with regularized linear regression, Optics Express 32 (9), 15147-15155, 2024.
  • Stef Molenaar, Tijmen Bos, Jim Boelrijk, Tina Dahlseid, Dwight Stoll, Bob Pirok, Computer-driven optimization of complex gradients in comprehensive two-dimensional liquid chromatography, https://doi.org/10.1016/j.chroma.2023.464306, J. Chromatogr. A, 2023.
  • David Ruhe, Johannes Brandstetter, Patrick Forré, Clifford Group Equivariant Neural Networks, https://arxiv.org/abs/2305.11141, NeurIPS 2023 (with oral presentation).
  • Fiona Lippert, Bart Kranstauber, Emiel van Loon, Patrick Forré, Deep Gaussian Markov Random Fields for Graph-Structured Dynamical Systems, https://arxiv.org/abs/2306.08445, NeurIPS 2023.
  • Miriam Rateike, Isabel Valera, Patrick Forré, Designing Long-term Group Fair Policies in Dynamical Systems, https://arxiv.org/abs/2311.12447, slidelive, NeurIPS 2023 Workshop: Algorithmic Fairness through the Lens of Time (with oral presentation); https://doi.org/10.1145/3630106.3658538, ACM FAccT 2024.
  • Uddipta Bhardwaj, James Alvey, Benjamin Kurt Miller, Samaya Nissanke, Christoph Weniger, Peregrine: Sequential simulation-based inference for gravitational wave signals, https://arxiv.org/abs/2304.02035, American Physical Society Phys. Rev. D, 2023.
  • Teodora Pandeva, Patrick Forré, Multi-View Independent Component Analysis with Shared and Individual Sources, https://arxiv.org/abs/2210.02083, openreview, UAI 2023, PMLR 216:1639-1650, 2023.
  • David Ruhe, Jayesh K. Gupta, Steven de Keninck, Max Welling, Johannes Brandstetter, Geometric Clifford Algebra Networks, https://arxiv.org/abs/2302.06594, ICML 2023.
  • Benjamin Kurt Miller, Marco Federici, Christoph Weniger, Patrick Forré, Simulation-based Inference with the Generalized Kullback-Leibler Divergence, openreview, https://arxiv.org/abs/2310.01808, ICML 2023 Workshop: Synergy of Scientific and Machine Learning Modeling.
  • Arnaud Delaunoy, Benjamin Kurt Miller, Patrick Forré, Christoph Weniger, Gilles Louppe, Balancing Simulation-based Inference for Conservative Posteriors, https://arxiv.org/abs/2304.10978, openreview, AABI 2023.
  • Teodora Pandeva, Patrick Forré, Multi-View Independent Component Analysis for Omics Data Integration, openreview, ICLR 2023 Workshop: Machine Learning and Global Health.
  • Jim Boelrijk, Denice van Herwerden, Bernd Ensing, Patrick Forré, Saer Samanipour, Predicting RP-LC retention indices of structurally unknown chemicals from mass spectrometry data, doi:10.26434/chemrxiv-2022-85wcl, Journal of Cheminformatics 15 (1), 2023.
  • Kaitlin Maile, Dennis G. Wilson, Patrick Forré, Equivariance-aware Architectural Optimization of Neural Networks, ICLR 2023, openreview.
  • Jim Boelrijk, Bernd Ensing, Patrick Forré, Multi-objective optimization via equivariant deep hypervolume approximation, ICLR 2023, openreview.
  • Jim Boelrijk, Bernd Ensing, Patrick Forré, Bob Pirok, Closed-loop automatic gradient design for liquid chromatography using Bayesian optimization, Analytica Chimica Acta, 2023, 340789, https://doi.org/10.1016/j.aca.2023.340789.
  • Kaitlin Maile, Dennis George Wilson, Patrick Forré, Towards Architectural Optimization of Equivariant Neural Networks over Subgroups, NeurIPS 2022 Workshop: NeurReps, openreview.
  • David Ruhe, Kaze Wong, Miles Cranmer, Patrick Forré, Normalizing Flows for Hierarchical Bayesian Analysis: A Gravitational Wave Population Study, NeurIPS 2022 Workshop: Machine Learning and the Physical Sciences, https://arxiv.org/abs/2211.09008.
  • Fiona Lippert, Bart Kranstauber, Emiel van Loon, Patrick Forré, Physics-informed inference of aerial animal movements from weather radar data, NeurIPS 2022 Workshop: AI4Science, openreview.
  • Benjamin Kurt Miller, Christoph Weniger, Patrick Forré, Contrastive Neural Ratio Estimation, NeurIPS 2022, openreview, SlideLive.
  • Tijmen Bos, Jim Boelrijk, Stef Molenaar, Brian van’t Veer, Leon Niezen, Denice van Herwerden, Saer Samanipour, Dwight Stoll, Patrick Forré, Bernd Ensing, Govert Somsen, Bob Pirok, Chemometric Strategies for Fully Automated Interpretive Method Development in Liquid Chromatography, Anal. Chem., 2022, 94, 46, 16060-16068, https://doi.org/10.1021/acs.analchem.2c03160.
  • Alex Cole, Benjamin Kurt Miller, Samuel J. Witte, Maxwell X. Cai, Meiert W. Grootes, Francesco Nattino, Christoph Weniger, Fast and Credible Likelihood-Free Cosmology with Truncated Marginal Neural Ratio Estimation, https://arxiv.org/abs/2111.08030, Journal of Cosmology and Astroparticle Physics, 2022.
  • Fiona Lippert, Bart Kranstauber, Patrick Forré, Emiel van Loon, Learning to predict spatiotemporal movement dynamics from weather radar networks, Methods in Ecology and Evolution, 2022, 13 (12), 2811-2826, https://besjournals.onlinelibrary.wiley.com/doi/full/10.1111/2041-210X.14007.
  • Alex Cole, Benjamin Kurt Miller, Samuel J. Witte, Maxwell X. Cai, Meiert W. Grootes, Francesco Nattino, Christoph Weniger, Fast and Credible Likelihood-Free Cosmology with Truncated Marginal Neural Ratio Estimation, Journal of Cosmology and Astroparticle Physics, 2022, 004, https://doi.org/10.1088/1475-7516/2022/09/004.
  • Benjamin Kurt Miller, Alex Cole, Christoph Weniger, Francesco Nattino, Ou Ku, Meiert W. Grootes, swyft: Truncated Marginal Neural Ratio Estimation in Python, Journal of Open Source Software, 2022, 7 (75), 4205, https://doi.org/10.21105/joss.04205, code.
  • David Ruhe, Patrick Forré, Self-Supervised Inference in State-Space Models, ICLR 2022, openreview,
  • David Ruhe, Mark Kuiack, Antonia Rowlinson, Ralph Wijers, Patrick Forré, Detecting dispersed radio transients in real time using convolutional neural networks, Astronomy and Computing, vol. 38, 2022, https://doi.org/10.1016/j.ascom.2021.100512, https://arxiv.org/abs/2103.15418, code.
  • Jim Boelrijk, Bob Pirok, Bernd Ensing, Patrick Forré, Bayesian optimization of comprehensive two-dimensional liquid chromatography separations, J. Chromatogr. A, 2021, https://doi.org/10.1016/j.chroma.2021.462628
  • Benjamin Kurt Miller, Alex Cole, Patrick Forré, Gilles Louppe, Christoph Weniger, Truncated Marginal Neural Ratio Estimation, NeurIPS 2021, openreview.
  • Marco Federici, Ryota Tomioka, Patrick Forré, An Information-theoretic Approach to Distribution Shifts, NeurIPS 2021, https://arxiv.org/abs/2106.03783.
  • Emiel Hoogeboom, Didrik Nielsen, Priyank Jaini, Patrick Forré, Max Welling, Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions, NeurIPS 2021, https://arxiv.org/abs/2102.05379.
  • Christoph J. Hönes, Benjamin Kurt Miller, Ana M. Heras, Bernard H. Foing, Automatically detecting anomalous exoplanet transits, https://arxiv.org/abs/2111.08679, NeurIPS 2021 Workshop: Machine Learning and the Physical Sciences.
  • Stephan Bongers, Patrick Forré, Jonas Peters, Joris M. Mooij, Foundations of Structural Causal Models with Cycles and Latent Variables, Annals of Statistics, 49(5): 2885-2915, 2021, doi:10.1214/21-AOS2064, https://arxiv.org/abs/1611.06221.
  • Andrei Apostol, Maarten Stol, Patrick Forré, Pruning by leveraging training dynamics, AI Communications, 2021, doi:10.3233/AIC-210127.
  • Maximilian Ilse, Jakub M Tomczak, Patrick Forré, Selecting Data Augmentation for Simulating Interventions, ICML 2021, https://arxiv.org/abs/2005.01856.
  • T. Anderson Keller, Jorn W. T. Peters, Priyank Jaini, Emiel Hoogeboom, Patrick Forré, Max Welling, Self Normalizing Flows, ICML 2021, https://arxiv.org/abs/2011.07248.
  • Jose Gallego-Posada, Patrick Forré, Simplicial Regularization, ICLR 2021 Workshop: Geometrical and Topological Representation Learning, openreview.
  • Ferry Hooft, Alberto Pérez de Alba Ortíz, Bernd Ensing, Discovering Collective Variables of Molecular Transitions via Genetic Algorithms and Neural Networks, J. Chem. Theory Comput. 2021.
  • Benjamin Kurt Miller, Alex Cole, Gilles Louppe, Christoph Weniger, Simulation-efficient marginal posterior estimation with swyft: stop wasting your precious time, NeurIPS 2020 Workshop: Machine Learning and the Physical Sciences, https://arxiv.org/abs/2011.13951.
  • Andrei Apostol, Maarten Stol, Patrick Forré, FlipOut: Uncovering Redundant Weights via Sign Flipping, BNAIC/BeNeLearn 2020, best paper award, https://arxiv.org/abs/2009.02594.
  • Luca Falorsi, Patrick Forré, Neural Ordinary Differential Equations on Manifolds, ICML 2020 Workshop INNF+: Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models, https://arxiv.org/abs/2006.06663, SlideLive.
  • Marco Federici, Anjan Dutta, Patrick Forré, Nate Kushman, Zeynep Akata, Learning Robust Representations via Multi-View Information Bottleneck, ICLR 2020, https://arxiv.org/abs/2002.07017.

Preprints

  • Philip Boeken, Patrick Forré, Joris M. Mooij, Nonparametric Bayesian networks are typically faithful in the total variation metric, https://arxiv.org/abs/2410.16004, 2024.
  • Maximilian Lipp, Benjamin Kurt Miller, Lyubov V. Amitonova, Patrick Forré. Generalizing Coverage Plots for Simulation-based Inference, preprint, 2024.
  • Anuroop Sriram, Benjamin Kurt Miller. FlowLLM: Flow Matching for Material Generation with Learned Base Distributions, preprint, 2024.
  • Leon Lang, Clélia de Mulatier, Rick Quax, Patrick Forré, Abstract Markov Random Fields, https://arxiv.org/abs/2407.02134, 2024.
  • Lukas Fluri, Leon Lang, Alessandro Abate, Patrick Forré, David Krueger, Joar Skalse, The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret, https://arxiv.org/abs/2406.15753, 2024.
  • Marco Federici, David Ruhe, Patrick Forré, On the Effectiveness of Hybrid Mutual Information Estimation, https://arxiv.org/abs/2306.00608, 2023.
  • Patrick Forré, Quasi-Measurable Spaces, https://arxiv.org/abs/2109.11631, 2021.
  • Maurice Weiler, Patrick Forré, Erik Verlinde, Max Welling, Coordinate Independent Convolutional Networks - Isometry and Gauge Equivariant Convolutions on Riemannian Manifolds, https://arxiv.org/abs/2106.06020, 2021.
  • Patrick Forré, Transitional Conditional Independence, https://arxiv.org/abs/2104.11547, 2021.
  • Maximilian Ilse, Patrick Forré, Max Welling, Joris M. Mooij, Efficient Causal Inference from Combined Observational and Interventional Data through Causal Reductions, https://arxiv.org/abs/2103.04786, 2021.
  • Rik Helwegen, Christos Louizos, Patrick Forré, Improving Fair Predictions Using Variational Inference in Causal Models, https://arxiv.org/abs/2008.10880, 2020.
  • Stijn Verdenius, Maarten Stol, Patrick Forré, Pruning via Iterative Ranking of Sensitivity Statistics, https://arxiv.org/abs/2006.00896, 2020.

Back to Books or Publications or Preprints.