Michael Arbel

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 45

Top Topics

Reinforcement Learning

Natural Gradient

Probability Measures

Top Venues

Publications

Michael Arbel, Alexandre Zouaoui
MLXP: A framework for conducting replicable Machine Learning eXperiments in Python. CoRR (2024)
Juliette Marrie, Michael Arbel, Julien Mairal, Diane Larlus
On Good Practices for Task-Specific Distillation of Large Pretrained Visual Models. Trans. Mach. Learn. Res. 2024 (2024)
Ieva Petrulionyte, Julien Mairal, Michael Arbel
Functional Bilevel Optimization for Machine Learning. CoRR (2024)
Juliette Marrie, Michael Arbel, Julien Mairal, Diane Larlus
On Good Practices for Task-Specific Distillation of Large Pretrained Models. CoRR (2024)
Michael Arbel, Alexandre Zouaoui
MLXP: A framework for conducting replicable experiments in Python. ACM-REP (2024)
Michael Arbel, Romain Menegaux, Pierre Wolinski
Rethinking Gauss-Newton for learning over-parameterized models. NeurIPS (2023)
Juliette Marrie, Michael Arbel, Diane Larlus, Julien Mairal
SLACK: Stable Learning of Augmentations with Cold-start and KL regularization. CoRR (2023)
Michael Arbel
Rethinking Gauss-Newton for learning over-parameterized models. CoRR (2023)
Juliette Marrie, Michael Arbel, Diane Larlus, Julien Mairal
SLACK: Stable Learning of Augmentations with Cold-Start and KL Regularization. CVPR (2023)
Michael Arbel, Julien Mairal
Amortized Implicit Differentiation for Stochastic Bilevel Optimization. ICLR (2022)
Ted Moskovitz, Michael Arbel, Jack Parker-Holder, Aldo Pacchiano
Towards an Understanding of Default Policies in Multitask Policy Optimization. AISTATS (2022)
Michael Arbel, Julien Mairal
Non-Convex Bilevel Games with Critical Point Selection Maps. NeurIPS (2022)
Alexander G. de G. Matthews, Michael Arbel, Danilo Jimenez Rezende, Arnaud Doucet
Continual Repeated Annealed Flow Transport Monte Carlo. ICML (2022)
Alexander G. de G. Matthews, Michael Arbel, Danilo J. Rezende, Arnaud Doucet
Continual Repeated Annealed Flow Transport Monte Carlo. CoRR (2022)
Pierre Glaser, Michael Arbel, Arnaud Doucet, Arthur Gretton
Maximum Likelihood Learning of Energy-Based Models for Simulation-Based Inference. CoRR (2022)
Michael Arbel, Alexander G. de G. Matthews, Arnaud Doucet
Annealed Flow Transport Monte Carlo. ICML (2021)
Louis Thiry, Michael Arbel, Eugene Belilovsky, Edouard Oyallon
The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods. CoRR (2021)
Pierre Glaser, Michael Arbel, Arthur Gretton
KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Support. CoRR (2021)
Michael Arbel, Julien Mairal
Amortized Implicit Differentiation for Stochastic Bilevel Optimization. CoRR (2021)
Pierre Glaser, Michael Arbel, Arthur Gretton
KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Support. NeurIPS (2021)
Ted Moskovitz, Michael Arbel, Jack Parker-Holder, Aldo Pacchiano
Towards an Understanding of Default Policies in Multitask Policy Optimization. CoRR (2021)
Ted Moskovitz, Michael Arbel, Ferenc Huszar, Arthur Gretton
Efficient Wasserstein Natural Gradients for Reinforcement Learning. ICLR (2021)
Ted Moskovitz, Jack Parker-Holder, Aldo Pacchiano, Michael Arbel, Michael I. Jordan
Tactical Optimism and Pessimism for Deep Reinforcement Learning. NeurIPS (2021)
Michael Arbel, Liang Zhou, Arthur Gretton
Generalized Energy Based Models. ICLR (2021)
Michael Arbel, Alexander G. de G. Matthews, Arnaud Doucet
Annealed Flow Transport Monte Carlo. CoRR (2021)
Ted Moskovitz, Jack Parker-Holder, Aldo Pacchiano, Michael Arbel
Deep Reinforcement Learning with Dynamic Optimism. CoRR (2021)
Louis Thiry, Michael Arbel, Eugene Belilovsky, Edouard Oyallon
The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods. ICLR (2021)
Anna Korba, Adil Salim, Michael Arbel, Giulia Luise, Arthur Gretton
A Non-Asymptotic Analysis for Stein Variational Gradient Descent. CoRR (2020)
Tolga Birdal, Michael Arbel, Umut Simsekli, Leonidas J. Guibas
Synchronizing Probability Measures on Rotations via Optimal Transport. CVPR (2020)
Ted Moskovitz, Michael Arbel, Ferenc Huszar, Arthur Gretton
Efficient Wasserstein Natural Gradients for Reinforcement Learning. CoRR (2020)
Anna Korba, Adil Salim, Michael Arbel, Giulia Luise, Arthur Gretton
A Non-Asymptotic Analysis for Stein Variational Gradient Descent. NeurIPS (2020)
Samuel Cohen, Michael Arbel, Marc Peter Deisenroth
Estimating Barycenters of Measures in High Dimensions. CoRR (2020)
Tolga Birdal, Michael Arbel, Umut Simsekli, Leonidas J. Guibas
Synchronizing Probability Measures on Rotations via Optimal Transport. CoRR (2020)
Michael Arbel, Liang Zhou, Arthur Gretton
KALE: When Energy-Based Learning Meets Adversarial Training. CoRR (2020)
Michael Arbel, Arthur Gretton, Wuchen Li, Guido Montúfar
Kernelized Wasserstein Natural Gradient. ICLR (2020)
Michael Arbel, Anna Korba, Adil Salim, Arthur Gretton
Maximum Mean Discrepancy Gradient Flow. NeurIPS (2019)
Michael Arbel, Anna Korba, Adil Salim, Arthur Gretton
Maximum Mean Discrepancy Gradient Flow. CoRR (2019)
Michael Arbel, Arthur Gretton, Wuchen Li, Guido Montúfar
Kernelized Wasserstein Natural Gradient. CoRR (2019)
Mikolaj Binkowski, Danica J. Sutherland, Michael Arbel, Arthur Gretton
Demystifying MMD GANs. ICLR (Poster) (2018)
Danica J. Sutherland, Heiko Strathmann, Michael Arbel, Arthur Gretton
Efficient and principled score estimation with Nyström kernel exponential families. AISTATS (2018)
Mikolaj Binkowski, Danica J. Sutherland, Michael Arbel, Arthur Gretton
Demystifying MMD GANs. CoRR (2018)
Michael Arbel, Danica J. Sutherland, Mikolaj Binkowski, Arthur Gretton
On gradient regularizers for MMD GANs. NeurIPS (2018)
Michael Arbel, Danica J. Sutherland, Mikolaj Binkowski, Arthur Gretton
On gradient regularizers for MMD GANs. CoRR (2018)
Michael Arbel, Arthur Gretton
Kernel Conditional Exponential Family. AISTATS (2018)
Danica J. Sutherland, Heiko Strathmann, Michael Arbel, Arthur Gretton
Efficient and principled score estimation. CoRR (2017)