623 citations
- The University of TokyoJP31 papers
- Tokyo Institute of TechnologyJP24 papers
- École PolytechniqueFR16 papers
- Future University HakodateJP10 papers
- Laboratoire d'Informatique de l'École PolytechniqueFR10 papers
- Data61AU9 papers
- Centre National de la Recherche ScientifiqueFR8 papers
- Chuo UniversityJP6 papers
- Sony Corporation (United States)US6 papers
- Keio UniversityJP5 papers
- Kyoto UniversityJP5 papers
- Sapienza University of RomeIT5 papers
10 papers · 1 filter
On a generalization of the Jensen-Shannon divergence
Frank Nielsen
The Jensen-Shannon divergence is a renown bounded symmetrization of the Kullback-Leibler divergence which does not require probability densities to have matching supports. In this…
Continuous Value Iteration (CVI) Reinforcement Learning and Imaginary Experience Replay (IER) for learning multi-goal, continuous action and state space controllers
Andreas Gerken, Michael Spranger
This paper presents a novel model-free Reinforcement Learning algorithm for learning behavior in continuous action, state, and goal spaces. The algorithm approximates optimal value…
Generalized Gibbs Ensembles in Discrete Quantum Gravity
Goffredo Chirco, Isha Kotecha
Maximum entropy principle and Souriau's symplectic generalization of Gibbs states have provided crucial insights leading to extensions of standard equilibrium statistical mechanics…
Mind2Mind : transfer learning for GANs
Yaël Frégier, Jean-Baptiste Gouray
Training generative adversarial networks (GANs) on high quality (HQ) images involves important computing resources. This requirement represents a bottleneck for the development of…
A closed-form formula for the Kullback-Leibler divergence between Cauchy distributions
Frédéric Chyzak, Frank Nielsen
We report a closed-form expression for the Kullback-Leibler divergence between Cauchy distributions which involves the calculation of a novel definite integral. The formula shows t…
A Geometric Modeling of Occam's Razor in Deep Learning
Ke Sun, Frank Nielsen
Why do deep neural networks (DNNs) benefit from very high dimensional parameter spaces? Their huge parameter complexities vs stunning performance in practice is all the more intrig…