70 citations
- Arizona State UniversityUS2 papers
- Carnegie Mellon UniversityUS2 papers
- Robert Bosch (Germany)DE2 papers
- Technion – Israel Institute of TechnologyIL2 papers
- University of AmsterdamNL2 papers
- University of BaselCH2 papers
- University of FreiburgDE2 papers
- Department of Physics, Mathematics and InformaticsBY1 paper
- Indian Institute of Technology KanpurIN1 paper
- Karlsruhe Institute of TechnologyDE1 paper
- Lawrence Livermore National LaboratoryUS1 paper
- Massachusetts Institute of TechnologyUS1 paper
11 papers · 1 filter
Inferring the Structure of Ordinary Differential Equations
Juliane Weilbach, Sebastian Gerwinn, Christian Weilbach +1
Understanding physical phenomena oftentimes means understanding the underlying dynamical system that governs observational measurements. While accurate prediction can be achieved w…
High-Dimensional Bayesian Optimization via Nested Riemannian Manifolds
Noémie Jaquier, Leonel Rozo
Despite the recent success of Bayesian optimization (BO) in a variety of applications where sample efficiency is imperative, its performance may be seriously compromised in setting…
Qgraph-bounded Q-learning: Stabilizing Model-Free Off-Policy Deep Reinforcement Learning
Sabrina Hoppe, Marc Toussaint
In state of the art model-free off-policy deep reinforcement learning, a replay memory is used to store past experience and derive all network updates. Even if both state and actio…
Provably robust deep generative models
Filipe Condessa, Zico Kolter
Recent work in adversarial attacks has developed provably robust methods for training deep neural network classifiers. However, although they are often mentioned in the context of…
Model adaptation and unsupervised learning with non-stationary batch data under smooth concept drift
Subhro Das, Prasanth Lade, Soundar Srinivasan
Most predictive models assume that training and test data are generated from a stationary process. However, this assumption does not hold true in practice. In this paper, we consid…
Differential Bayesian Neural Nets
Andreas Look, Melih Kandemir
Neural Ordinary Differential Equations (N-ODEs) are a powerful building block for learning systems, which extend residual networks to a continuous-time dynamical system. We propose…