10.9k citations
- Max Planck SocietyDE155 papers
- Heidelberg UniversityDE52 papers
- Centre National de la Recherche ScientifiqueFR46 papers
- Jagiellonian UniversityPL44 papers
- Charles UniversityCZ40 papers
- Polish Academy of SciencesPL40 papers
- Humboldt-Universität zu BerlinDE39 papers
- European Organization for Nuclear ResearchCH38 papers
- Institut National de Physique Nucléaire et de Physique des ParticulesFR37 papers
- University of BirminghamGB37 papers
- University of OxfordGB36 papers
- Rutherford Appleton LaboratoryGB35 papers
7 papers · 1 filter
Hierarchical Reinforcement Learning with Timed Subgoals
Nico Gürtler, Dieter Büchler, Georg Martius
Hierarchical reinforcement learning (HRL) holds great potential for sample-efficient learning on challenging long-horizon tasks. In particular, letting a higher level assign subgoa…
Fast and Slow Learning of Recurrent Independent Mechanisms
Kanika Madan, Nan Rosemary Ke, Anirudh Goyal +2
Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning agent interacting with its environment is l…
Dirichlet Pruning for Neural Network Compression
Kamil Adamczewski, Mijung Park
We introduce Dirichlet pruning, a novel post-processing technique to transform a large neural network model into a compressed one. Dirichlet pruning is a form of structured pruning…
More Powerful Selective Kernel Tests for Feature Selection
Jen Ning Lim, Makoto Yamada, Wittawat Jitkrittum +3
Refining one's hypotheses in the light of data is a common scientific practice; however, the dependency on the data introduces selection bias and can lead to specious statistical a…
A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe
Francesco Locatello, Rajiv Khanna, Michael Tschannen +1
Two of the most fundamental prototypes of greedy optimization are the matching pursuit and Frank-Wolfe algorithms. In this paper, we take a unified view on both classes of methods,…
Extrapolation and learning equations
Georg Martius, Christoph H. Lampert
In classical machine learning, regression is treated as a black box process of identifying a suitable function from a hypothesis set without attempting to gain insight into the mec…