Michael Arbel
Michael Arbel
Gatsby Computational Neuroscience Unit, UCL
Verified email at ucl.ac.uk - Homepage
Cited by
Cited by
Demystifying mmd gans
M Bińkowski, DJ Sutherland, M Arbel, A Gretton
International Conference on Learning Representations, 2018
On gradient regularizers for MMD GANs
M Arbel, DJ Sutherland, M Bińkowski, A Gretton
arXiv preprint arXiv:1805.11565, 2018
Maximum mean discrepancy gradient flow
M Arbel, A Korba, A Salim, A Gretton
arXiv preprint arXiv:1906.04370, 2019
Efficient and principled score estimation with Nystr\" om kernel exponential families
DJ Sutherland, H Strathmann, M Arbel, A Gretton
Proceedings of the Twenty-First International Conference on Artificial …, 2018
Kernel conditional exponential family
M Arbel, A Gretton
Proceedings of the Twenty-First International Conference on Artificial …, 2018
A non-asymptotic analysis for Stein variational gradient descent
A Korba, A Salim, M Arbel, G Luise, A Gretton
Advances in Neural Information Processing Systems 33, 2020
Generalized Energy Based Models
M Arbel, L Zhou, A Gretton
arXiv preprint arXiv:2003.05033, 2020
Synchronizing probability measures on rotations via optimal transport
T Birdal, M Arbel, U Simsekli, LJ Guibas
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020
Kernelized Wasserstein Natural Gradient
M Arbel, A Gretton, W Li, G Montúfar
arXiv preprint arXiv:1910.09652, 2019
Estimating barycenters of measures in high dimensions
S Cohen, M Arbel, MP Deisenroth
arXiv preprint arXiv:2007.07105, 2020
Efficient wasserstein natural gradients for reinforcement learning
T Moskovitz, M Arbel, F Huszar, A Gretton
arXiv preprint arXiv:2010.05380, 2020
Annealed Flow Transport Monte Carlo
M Arbel, AGDG Matthews, A Doucet
arXiv preprint arXiv:2102.07501, 2021
Deep Reinforcement Learning with Dynamic Optimism
T Moskovitz, J Parker-Holder, A Pacchiano, M Arbel, M Jordan
arXiv preprint arXiv:2102.03765, 2021
KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Support
P Glaser, M Arbel, A Gretton
arXiv preprint arXiv:2106.08929, 2021
Methods for Optimization and Regularization of Generative Models
M Arbel
UCL (University College London), 2021
The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods
L Thiry, M Arbel, E Belilovsky, E Oyallon
arXiv preprint arXiv:2101.07528, 2021
Synchronizing Probability Measures on Rotations via Optimal Transport Open Website
T Birdal, M Arbel, U Şimşekli, L Guibas
The system can't perform the operation now. Try again later.
Articles 1–17