Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Andreas Krause

Andreas Krause

Department of Computer Science, ETH Zürich

Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking


Nov 15, 2021
Octavian-Eugen Ganea, Xinyuan Huang, Charlotte Bunne, Yatao Bian, Regina Barzilay, Tommi Jaakkola, Andreas Krause


  Access Paper or Ask Questions

Misspecified Gaussian Process Bandit Optimization


Nov 09, 2021
Ilija Bogunovic, Andreas Krause

* Accepted to NeurIPS 2021 

  Access Paper or Ask Questions

Risk-averse Heteroscedastic Bayesian Optimization


Nov 05, 2021
Anastasiia Makarova, Ilnura Usmanova, Ilija Bogunovic, Andreas Krause


  Access Paper or Ask Questions

Learning Stable Deep Dynamics Models for Partially Observed or Delayed Dynamical Systems


Oct 27, 2021
Andreas Schlaginhaufen, Philippe Wenk, Andreas Krause, Florian Dörfler

* Advances in Neural Information Processing Systems, 2021 
* Published at NeurIPS 2021 

  Access Paper or Ask Questions

Diversified Sampling for Batched Bayesian Optimization with Determinantal Point Processes


Oct 22, 2021
Elvis Nava, Mojmír Mutný, Andreas Krause


  Access Paper or Ask Questions

Sensing Cox Processes via Posterior Sampling and Positive Bases


Oct 21, 2021
Mojmír Mutný, Andreas Krause


  Access Paper or Ask Questions

Hierarchical Skills for Efficient Exploration


Oct 20, 2021
Jonas Gehring, Gabriel Synnaeve, Andreas Krause, Nicolas Usunier

* To appear in 35th Conference on Neural Information Processing Systems (NeurIPS 2021) 

  Access Paper or Ask Questions

Data Summarization via Bilevel Optimization


Sep 26, 2021
Zalán Borsos, Mojmír Mutný, Marco Tagliasacchi, Andreas Krause


  Access Paper or Ask Questions

Contextual Games: Multi-Agent Learning with Side Information


Jul 13, 2021
Pier Giuseppe Sessa, Ilija Bogunovic, Andreas Krause, Maryam Kamgarpour

* Proc. of Neural Information Processing Systems (NeurIPS), 2020 

  Access Paper or Ask Questions

Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning


Jul 08, 2021
Barna Pasztor, Ilija Bogunovic, Andreas Krause

* 28 pages, 2 figures, Preprint, Submitted to NeurIPS 2021 

  Access Paper or Ask Questions

Neural Contextual Bandits without Regret


Jul 07, 2021
Parnian Kassraie, Andreas Krause

* 37 pages, 6 figures 

  Access Paper or Ask Questions

Distributional Gradient Matching for Learning Uncertain Neural Dynamics Models


Jun 22, 2021
Lenart Treven, Philippe Wenk, Florian Dörfler, Andreas Krause


  Access Paper or Ask Questions

PopSkipJump: Decision-Based Attack for Probabilistic Classifiers


Jun 14, 2021
Carl-Johann Simon-Gabriel, Noman Ahmed Sheikh, Andreas Krause

* ICML'21. Code available at https://github.com/cjsg/PopSkipJump . 9 pages & 7 figures in main part, 14 pages & 10 figures in appendix 

  Access Paper or Ask Questions

JKOnet: Proximal Optimal Transport Modeling of Population Dynamics


Jun 11, 2021
Charlotte Bunne, Laetitia Meng-Papaxanthos, Andreas Krause, Marco Cuturi


  Access Paper or Ask Questions

Bias-Robust Bayesian Optimization via Dueling Bandits


Jun 09, 2021
Johannes Kirschner, Andreas Krause


  Access Paper or Ask Questions

Robust Generalization despite Distribution Shift via Minimum Discriminating Information


Jun 08, 2021
Tobias Sutter, Andreas Krause, Daniel Kuhn

* 23 pages, 4 figures 

  Access Paper or Ask Questions

Meta-Learning Reliable Priors in the Function Space


Jun 06, 2021
Jonas Rothfuss, Dominique Heyn, Jinfan Chen, Andreas Krause

* 23 pages 

  Access Paper or Ask Questions

Energy-Based Learning for Cooperative Games, with Applications to Feature/Data/Model Valuations


Jun 05, 2021
Yatao Bian, Yu Rong, Tingyang Xu, Jiaxiang Wu, Andreas Krause, Junzhou Huang


  Access Paper or Ask Questions

Addressing the Long-term Impact of ML Decisions via Policy Regret


Jun 02, 2021
David Lindner, Hoda Heidari, Andreas Krause

* Accepted to IJCAI 2021 

  Access Paper or Ask Questions

Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximation


May 29, 2021
Mikhail Usvyatsov, Anastasia Makarova, Rafael Ballester-Ripoll, Maxim Rakhuba, Andreas Krause, Konrad Schindler


  Access Paper or Ask Questions

Near-Optimal Multi-Perturbation Experimental Design for Causal Structure Learning


May 28, 2021
Scott Sussex, Andreas Krause, Caroline Uhler

* 9 pages, 2 figures 

  Access Paper or Ask Questions

DiBS: Differentiable Bayesian Structure Learning


May 25, 2021
Lars Lorch, Jonas Rothfuss, Bernhard Schölkopf, Andreas Krause


  Access Paper or Ask Questions

Bias-Robust Bayesian Optimization via Dueling Bandit


May 25, 2021
Johannes Kirschner, Andreas Krause


  Access Paper or Ask Questions

Regret Bounds for Gaussian-Process Optimization in Large Domains


Apr 29, 2021
Manuel Wüthrich, Bernhard Schölkopf, Andreas Krause


  Access Paper or Ask Questions

Overfitting in Bayesian Optimization: an empirical study and early-stopping solution


Apr 16, 2021
Anastasia Makarova, Huibin Shen, Valerio Perrone, Aaron Klein, Jean Baptiste Faddoul, Andreas Krause, Matthias Seeger, Cedric Archambeau


  Access Paper or Ask Questions

Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning


Mar 18, 2021
Sebastian Curi, Ilija Bogunovic, Andreas Krause


  Access Paper or Ask Questions

Information Directed Reward Learning for Reinforcement Learning


Feb 24, 2021
David Lindner, Matteo Turchetta, Sebastian Tschiatschek, Kamil Ciosek, Andreas Krause


  Access Paper or Ask Questions

Risk-Averse Offline Reinforcement Learning


Feb 10, 2021
Núria Armengol Urpí, Sebastian Curi, Andreas Krause


  Access Paper or Ask Questions

Efficient Pure Exploration for Combinatorial Bandits with Semi-Bandit Feedback


Jan 21, 2021
Marc Jourdan, Mojmír Mutný, Johannes Kirschner, Andreas Krause

* 45 pages. 3 tables. Appendices: from A to I. Figures: 1(a), 1(b), 2(a), 2(b), 3(a), 3(b), 3(c), 4(a), 4(b), 5(a), 5(b), 5(c), 5(d), 6(a), 6(b). To be published in the 32nd International Conference on Algorithmic Learning Theory and the Proceedings of Machine Learning Research vol 132:1-45, 2021 

  Access Paper or Ask Questions

Safe and Efficient Model-free Adaptive Control via Bayesian Optimization


Jan 19, 2021
Christopher König, Matteo Turchetta, John Lygeros, Alisa Rupenyan, Andreas Krause


  Access Paper or Ask Questions