Philippe Wenk PhD Student philippe.wenk@inf.ethz.ch CAB E 65.2 +41 44 632 98 93 Publications 2021 Learning Stable Deep Dynamics Models for Partially Observed or Delayed Dynamical Systems A. Schlaginhaufen, P. Wenk, A. Krause, F. DörflerIn Proc. Neural Information Processing Systems (NeurIPS), 2021[bibtex] [abstract] [pdf] Distributional Gradient Matching for Learning Uncertain Neural Dynamics Models L. Treven, P. Wenk, F. Dörfler, A. KrauseIn Proc. Neural Information Processing Systems (NeurIPS), 2021[bibtex] [abstract] [pdf] 2020 A Real-Robot Dataset for Assessing Transferability of Learned Dynamics Models D. Agudelo-España, A. Zadaianchuk, P. Wenk, A. Garg, J. Akpo, F. Grimminger, J. Viereck, M. Naveau, L. Righetti, G. Martius, A. Krause, B. Schölkopf, S. Bauer, M. WüthrichIn 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020[bibtex] [abstract] [doi] SLEIPNIR: Deterministic and Provably Accurate Feature Expansion for Gaussian Process Regression with Derivatives E. Angelis, P. Wenk, B. Schölkopf, S. Bauer, A. KrauseIn arXiv preprint arXiv:2003.02658, 2020[bibtex] [abstract] ODIN: ODE-Informed Regression for Parameter and State Inference in Time-Continuous Dynamical Systems P. Wenk, G. Abbati, S. Bauer, M. A. Osborne, A. Krause, B. SchölkopfIn Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI), 2020[bibtex] [abstract] [pdf] 2019 AReS and MaRS – Adversarial and MMD-Minimizing Regression for SDEs G. Abbati, P. Wenk, S. Bauer, M. A. Osborne, A. Krause, B. SchölkopfIn Proc. International Conference on Machine Learning (ICML), 2019Oral presentation[bibtex] [abstract] [pdf] Fast Gaussian process based gradient matching for parameter identification in systems of nonlinear ODEs P. Wenk, A. Gotovos, S. Bauer, N. S. Gorbach, A. Krause, J. M. BuhmannIn International Conference on Artificial Intelligence and Statistics (AISTATS), 2019[bibtex] [abstract] [pdf]
