AMLab | Amsterdam Machine Learning Lab

amlablogo.png

The Amsterdam Machine Learning Lab (AMLab) conducts research in machine learning, artificial intelligence, and its applications to large scale data domains in science and industry. This includes the development of deep generative models, methods for approximate inference, probabilistic programming, Bayesian deep learning, causal inference, reinforcement learning, graph neural networks, and geometric deep learning.

AMLab comprises 8 faculty. Max Welling and Jan-Willem van de Meent serve as co-directors. Herke van Hoof, Patrick Forré, Eric Nalisnick, Erik Bekkers, Christian Naesseth, and Sara Magliacane serve as tenure-track faculty. The lab participates in partnerships with industry through the QUvA Lab (with Qualcomm) and the Delta Lab (with Bosch). The lab also engages in cross-disciplinary collaborations through the AI4Science Lab.

News

Nov 17, 2022 Max Welling, Jan-Willem van de Meent and Alfons Hoekstra have a PhD opening on Learning PDEs. Deadline for applications is 16 December. Apply here.
Oct 25, 2022 Dr. Sara Magliacane is moving from the INDElab to join AMLab as a tenure-track assistant professor. This move strengthens the collaboration between the two groups under the ELLIS umbrella. She will continue working on causality and applications of causality to machine learning. Welcome to Sara!
Sep 5, 2022 Sindy Löwe received Google PhD Fellowship! What a wonderful acknowledgement of her as a top ML researcher!
Jul 19, 2022 AMLab will be presenting 8 papers at ICML 2022! Please see our blog for a full list.
May 18, 2022 Erik Bekkers has been named Lecturer of the Year for the FNWI. Congratulations to Erik for this fantastic achievement!
May 16, 2022 In addition to hiring for PhD positions, Jan-Willem van de Meent and Eric Nalisnick have a Postdoc opening as part of the UvA Bosch Delta Lab. Deadline for applications is June 10. Apply here!
May 5, 2022 Jan-Willem van de Meent and Eric Nalisnick are hiring for multiple PhD positions as part of our collaboration with the Bosch Center for Artificial Intelligence. Deadline is June 6. Apply here!
Mar 18, 2022 We are delighted to announce that we have renewed our collaboration with Bosch through the Delta Lab! Over the next 4 years, this lab will fund 10 students and postdocs, who will be advised by Eric Nalisnick, Jan-Willem van de Meent, Max Welling, and Theo Gevers. More information in this press release.

Recent Publications

  1. ICLR
    Bridge the Inference Gaps of Neural Processes via Expectation Maximization
    Wang, Qi, Federici, Marco, and Hoof, Herke
    In International Conference on Learning Representations 2023
  2. ICLR
    Sampling-Based Inference for Large Linear Models, with Application to Linearised Laplace
    Antorán, Javier, Padhy, Shreyas, Barbano, Riccardo, Nalisnick, Eric, Janz, David, and Miguel Hernández-Lobato, José
    In International Conference on Learning Representations 2023
  3. AISTATS
    Do Bayesian Neural Networks Need To Be Fully Stochastic?
    Sharma, Mrinank, Farquhar, Sebastian, Nalisnick, Eric, and Rainforth, Tom
    In Proceedings of The 26th International Conference on Artificial Intelligence and Statistics 2023
  4. AISTATS
    Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles
    Verma, Rajeev, Barrejón, Daniel, and Nalisnick, Eric
    In Proceedings of The 26th International Conference on Artificial Intelligence and Statistics 2023
  5. IJCNN
    Logic-based AI for Interpretable Board Game Winner Prediction with Tsetlin Machine
    Giri, Charul, Granmo, Ole-Christopher, Hoof, Herke, and Blakely, Christian D.
    In International Joint Conference on Neural Networks 2022
  6. NeurIPS
    Learning Expressive Meta-Representations with Mixture of Expert Neural Processes
    Wang, Qi, and Hoof, Herke
    In Advances in Neural Information Processing Systems 2022
  7. NeurIPS
    Factored Adaptation for Non-Stationary Reinforcement Learning
    Feng, Fan, Huang, Biwei, Zhang, Kun, and Magliacane, Sara
    In Advances in Neural Information Processing Systems 2022
  8. NeurIPS
    Neural Topological Ordering for Computation Graphs
    Gagrani, Mukul, Rainone, Corrado, Yang, Yang, Teague, Harris, Jeon, Wonseok, Hoof, Herke, Zeng, Weiliang Will, Zappi, Piero, Lott, Christopher, and Bondesan, Roberto
    In Advances in Neural Information Processing Systems 2022
  9. ICML
    Equivariant diffusion for molecule generation in 3d
    Hoogeboom, Emiel, Satorras, Vı́ctor Garcia, Vignac, Clément, and Welling, Max
    In International Conference on Machine Learning 2022
  10. ICML
    Lie Point Symmetry Data Augmentation for Neural PDE Solvers
    Brandstetter, Johannes, Welling, Max, and Worrall, Daniel E
    In International Conference on Machine Learning 2022
  11. ICML
    Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups
    Knigge, David M, Romero, David W, and Bekkers, Erik J
    International Conference on Machine Learning 2022
  12. ICML
    CITRIS: Causal Identifiability from Temporal Intervened Sequences
    Lippe, Phillip, Magliacane, Sara, Löwe, Sindy, Asano, Yuki M, Cohen, Taco, and Gavves, Efstratios
    International Conference on Machine Learning 2022
  13. ICML
    Learning Symmetric Embeddings for Equivariant World Models
    Park, Jung Yeon, Biza, Ondrej, Zhao, Linfeng, Meent, Jan-Willem, and Walters, Robin
    In International Conference on Machine Learning 2022
  14. ICML
    Adapting the Linearised Laplace Model Evidence for Modern Deep Learning
    Antoran, Javier, Janz, David, Allingham, James Urquhart, Daxberger, Erik, Barbano, Riccardo, Nalisnick, Eric, and Hernandez-Lobato, Jose Miguel
    In Proceedings of the 39th International Conference on Machine Learning 2022
  15. ICML
    Calibrated Learning to Defer with One-vs-All Classifiers
    Verma, Rajeev, and Nalisnick, Eric
    In Proceedings of the 39th International Conference on Machine Learning 2022
  16. ICML
    Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy Search
    Wang, Q., and Hoof, H.
    In International Conference on Machine Learning 2022
  17. MIDL
    Experimental design for MRI by greedy policy search
    Bakker, T., Muckley, M., Romero-Soriano, A., Drozdzal, M., and Pineda, L.
    In Proceedings of Machine Learning Research Jul 2022
  18. CLeaR
    Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data
    Löwe, S., Madras, D., Zemel, R., and Welling, M.
    Causal Learning and Reasoning Jul 2022
  19. ICLR
    Geometric and Physical Quantities improve E (3) Equivariant Message Passing
    Brandstetter, Johannes, Hesselink, Rob, Pol, Elise, Bekkers, Erik, and Welling, Max
    In International Conference on Learning Representations Jul 2022
  20. ICLR
    Self-Supervised Inference in State-Space Models
    Ruhe, David, and Forré, Patrick
    In International Conference on Learning Representations Jul 2022
  21. ASCOM
    Detecting dispersed radio transients in real time using convolutional neural networks
    Ruhe, David, Kuiack, Mark, Rowlinson, Antonia, Wijers, Ralph, and Forré, Patrick
    Astronomy and Computing Jul 2022
  22. ICLR
    Multi-Agent MDP Homomorphic Networks
    Pol, Elise, Hoof, Herke, Oliehoek, Frans, and Welling, Max
    In International Conference on Learning Representations Jul 2022
  23. CPAIOR
    Deep Policy Dynamic Programming for Vehicle Routing Problems
    Kool, Wouter, Hoof, Herke, Gromicho, Joaquim, and Welling, Max
    In International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research Jul 2022
  24. AAAI
    Fast and Data Efficient Reinforcement Learning from Pixels via Non-Parametric Value Approximation
    Long, Alex, Blair, Alan, and Hoof, Herke
    In AAAI National Conference on Artificial Intelligence Jul 2022
  25. IJCAI
    Value Refinement Network (VRN)
    Wöhlke, Jan, Schmitt, Felix, and Hoof, Herke
    In International Joint Conference on Artificial Intelligence Jul 2022
  26. IJCAI
    Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methods
    Höpner, Niklas, Tiddi, Ilaria, and Hoof, Herke
    In International Joint Conference on Artificial Intelligence Jul 2022
  27. NeurIPS
    Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders
    Keller, T. Anderson, Gao, Qinghe, and Welling, Max
    In SVRHM 2021 Workshop at NeurIPS Jul 2021
  28. ICCV
    Predictive Coding With Topographic Variational Autoencoders
    Keller, T. Anderson, and Welling, Max
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops Oct 2021
  29. NeurIPS
    Topographic VAEs learn Equivariant Capsules
    Keller, T. Anderson, and Welling, Max
    In Advances in Neural Information Processing Systems Oct 2021
  30. ICML
    Self Normalizing Flows
    Keller, T. Anderson, Peters, Jorn W.T., Jaini, Priyank, Hoogeboom, Emiel, Forré, Patrick, and Welling, Max
    In Proceedings of the 38th International Conference on Machine Learning 18–24 jul 2021
  31. NeurIPS
    As easy as APC: Leveraging self-supervised learning in the context of time series classification with varying levels of sparsity and severe class imbalance
    Wever, Fiorella, Keller, T. Anderson, Garcia, Victor, and Symul, Laura
    In Self-Supervised Learning Workshop at NeurIPS 18–24 jul 2021
  32. UAI
    Variational combinatorial sequential Monte Carlo methods for Bayesian phylogenetic inference
    Moretti, Antonio Khalil, Zhang, Liyi, Naesseth, Christian A., Venner, Hadiah, Blei, David, and Pe’er, Itsik
    In Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence 27–30 jul 2021
  33. AISTATS
    Rate-Regularization and Generalization in Variational Autoencoders
    Bozkurt, Alican, Esmaeili, Babak, Tristan, Jean-Baptiste, Brooks, Dana, Dy, Jennifer, and Meent, Jan-Willem
    In International Conference on Artificial Intelligence and Statistics Mar 2021
  34. NeurIPS
    Nested Variational Inference
    Zimmermann, Heiko, Wu, Hao, Esmaeili, Babak, and Meent, Jan-Willem
    In Advances in Neural Information Processing Systems Mar 2021
  35. ICML
    Conjugate Energy-Based Models
    Wu, Hao*, Esmaeili, Babak*, Wick, Michael, Tristan, Jean-Baptiste, and van de Meent, Jan-Willem
    In Proceedings of the 38th International Conference on Machine Learning (ICML) 18–24 jul 2021
  36. UAI
    Learning proposals for probabilistic programs with inference combinators
    Stites, Sam, Zimmermann, Heiko, Wu, Hao, Sennesh, Eli, and Meent, Jan-Willem
    In Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence 27–30 jul 2021
  37. AISTATS
    Predictive Complexity Priors
    Nalisnick, Eric, Gordon, Jonathan, and Miguel Hernandez-Lobato, Jose
    In Proceedings of The 24th International Conference on Artificial Intelligence and Statistics 13–15 apr 2021
  38. ICML
    Bayesian Deep Learning via Subnetwork Inference
    Daxberger, Erik, Nalisnick, Eric, Allingham, James U, Antoran, Javier, and Hernandez-Lobato, Jose Miguel
    In Proceedings of the 38th International Conference on Machine Learning 18–24 jul 2021
  39. JMLR
    Normalizing Flows for Probabilistic Modeling and Inference
    Papamakarios, George, Nalisnick, Eric, Rezende, Danilo Jimenez, Mohamed, Shakir, and Lakshminarayanan, Balaji
    Journal of Machine Learning Research 18–24 jul 2021
  40. JMS
    Optimizing Adaptive Notifications in Mobile Health Interventions Systems: Reinforcement Learning from a Data-driven Behavioral Simulator
    Wang, Shihan, Zhang, Chao, Kröse, Ben, and Hoof, Herke
    Journal of Medical Systems 18–24 jul 2021
  41. IJERPH
    Reinforcement Learning to Send Reminders at Right Moments in Smartphone Exercise Application: A Feasibility Study
    Wang, S., Sporrel, K., Hoof, H., Simons, M., Boer, R., Ettema, D., Nibbeling, N., Deutekom, M., and Kröse, B.
    International Journal of Environmental Research and Public Health, Special Issue 18–24 jul 2021
  42. ICRA
    Hierarchies of Planning and Reinforcement Learning for Robot Navigation
    Wöhlke, J., Schmitt, F., and Hoof, H.
    In IEEE International Conference on Robotics and Automation 18–24 jul 2021
  43. ICML
    Deep Coherent Exploration For Continuous Control
    Zhang, Yijie, and Hoof, Herke
    In International Conference on Machine Learning 18–24 jul 2021
  44. UrbComp
    Back to Basics: Deep Reinforcement Learning in Traffic Signal Control
    Kanis, S., Samson, L., Bloembergen, D., and Bakker, T.
    The 10th International Workshop on Urban Computing Nov 2021

Selected Publications

  1. NeurIPS
    MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning
    Pol, Elise, Worrall, Daniel, Hoof, Herke, Oliehoek, Frans, and Welling, Max
    In Advances in Neural Information Processing Systems 2020
  2. ICLR
    Estimating Gradients for Discrete Random Variables by Sampling without Replacement
    Kool, Wouter, Hoof, Herke, and Welling, Max
    In International Conference on Learning Representations 2020
  3. ICLR
    B-Spline CNNs on Lie groups
    Bekkers, Erik J
    In International Conference on Learning Representations 2019
  4. AISTATS
    Structured Disentangled Representations
    Esmaeili, Babak, Wu, Hao, Jain, Sarthak, Bozkurt, Alican, Siddharth, N., Paige, Brooks, Brooks, Dana H., Dy, Jennifer, and van de Meent, Jan-Willem
    Artificial Intelligence and Statistics 2019
  5. ICLR
    Do Deep Generative Models Know What They Don’t Know?
    Nalisnick, Eric, Matsukawa, Akihiro, Teh, Yee Whye, Gorur, Dilan, and Lakshminarayanan, Balaji
    In International Conference on Learning Representations 2019
  6. ESWC
    Modeling Relational Data with Graph Convolutional Networks
    Schlichtkrull, Michael, Kipf, Thomas N., Bloem, Peter, Berg, Rianne, Titov, Ivan, and Welling, Max
    In The Semantic Web: 15th International Conference, ESWC 2018, Heraklion, Crete, Greece 2018
  7. NeurIPS
    Learning Disentangled Representations with Semi-Supervised Deep Generative Models
    Siddharth, N., Paige, Brooks, Meent, Jan-Willem, Desmaison, Alban, Goodman, Noah D., Kohli, Pushmeet, Wood, Frank, and Torr, Philip
    In Advances in Neural Information Processing Systems 30 2017
  8. ICLR
    Semi-supervised classification with graph convolutional networks
    Kipf, Thomas N, and Welling, Max
    In International Conference on Learning Representations 2017
  9. ICML
    Group Equivariant Convolutional Networks
    Cohen, Taco, and Welling, Max
    In Proceedings of The 33rd International Conference on Machine Learning 20–22 jun 2016
  10. NeurIPS
    Improved Variational Inference with Inverse Autoregressive Flow
    Kingma, Durk P, Salimans, Tim, Jozefowicz, Rafal, Chen, Xi, Sutskever, Ilya, and Welling, Max
    In Advances in Neural Information Processing Systems 20–22 jun 2016
  11. NeurIPS
    Semi-Supervised Learning with Deep Generative Models
    Kingma, Durk P, Mohamed, Shakir, Jimenez Rezende, Danilo, and Welling, Max
    In Advances in Neural Information Processing Systems 20–22 jun 2014
  12. ICLR
    Auto-Encoding Variational Bayes
    Kingma, Diederik P., and Welling, Max
    20–22 jun 2013
  13. ICML
    Bayesian learning via stochastic gradient langevin dynamics
    Welling, Max, and Teh, Yee Whye
    In Proceedings of the 28th International Conference on Machine Learning, ICML 2011 20–22 jun 2011