Michael Arbel

According to our database, Michael Arbel authored at least 29 papers between 2017 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Functional Bilevel Optimization for Machine Learning.

Ieva Petrulionyte, Julien Mairal, Michael Arbel

CoRR, 2024

MLXP: A framework for conducting replicable Machine Learning eXperiments in Python.

Michael Arbel, Alexandre Zouaoui

CoRR, 2024

On Good Practices for Task-Specific Distillation of Large Pretrained Models.

Juliette Marrie, Michael Arbel, Julien Mairal, Diane Larlus

CoRR, 2024

2023

Rethinking Gauss-Newton for learning over-parameterized models.

Michael Arbel

CoRR, 2023

Rethinking Gauss-Newton for learning over-parameterized models.

Michael Arbel, Romain Menegaux, Pierre Wolinski

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

SLACK: Stable Learning of Augmentations with Cold-Start and KL Regularization.

Juliette Marrie, Michael Arbel, Diane Larlus, Julien Mairal

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

Maximum Likelihood Learning of Energy-Based Models for Simulation-Based Inference.

Pierre Glaser, Michael Arbel, Arnaud Doucet, Arthur Gretton

CoRR, 2022

Non-Convex Bilevel Games with Critical Point Selection Maps.

Michael Arbel, Julien Mairal

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Continual Repeated Annealed Flow Transport Monte Carlo.

Alexander G. de G. Matthews, Michael Arbel, Danilo Jimenez Rezende, Arnaud Doucet

Proceedings of the International Conference on Machine Learning, 2022

Amortized Implicit Differentiation for Stochastic Bilevel Optimization.

Michael Arbel, Julien Mairal

Proceedings of the Tenth International Conference on Learning Representations, 2022

Towards an Understanding of Default Policies in Multitask Policy Optimization.

Ted Moskovitz, Michael Arbel, Jack Parker-Holder, Aldo Pacchiano

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Deep Reinforcement Learning with Dynamic Optimism.

Ted Moskovitz, Jack Parker-Holder, Aldo Pacchiano, Michael Arbel

CoRR, 2021

Tactical Optimism and Pessimism for Deep Reinforcement Learning.

Ted Moskovitz, Jack Parker-Holder, Aldo Pacchiano, Michael Arbel, Michael I. Jordan

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Support.

Pierre Glaser, Michael Arbel, Arthur Gretton

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Annealed Flow Transport Monte Carlo.

Michael Arbel, Alexander G. de G. Matthews, Arnaud Doucet

Proceedings of the 38th International Conference on Machine Learning, 2021

The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods.

Louis Thiry, Michael Arbel, Eugene Belilovsky, Edouard Oyallon

Proceedings of the 9th International Conference on Learning Representations, 2021

Efficient Wasserstein Natural Gradients for Reinforcement Learning.

Ted Moskovitz, Michael Arbel, Ferenc Huszar, Arthur Gretton

Proceedings of the 9th International Conference on Learning Representations, 2021

Generalized Energy Based Models.

Michael Arbel, Liang Zhou, Arthur Gretton

Proceedings of the 9th International Conference on Learning Representations, 2021

2020

Estimating Barycenters of Measures in High Dimensions.

Samuel Cohen, Michael Arbel, Marc Peter Deisenroth

CoRR, 2020

KALE: When Energy-Based Learning Meets Adversarial Training.

Michael Arbel, Liang Zhou, Arthur Gretton

CoRR, 2020

A Non-Asymptotic Analysis for Stein Variational Gradient Descent.

Anna Korba, Adil Salim, Michael Arbel, Giulia Luise, Arthur Gretton

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Kernelized Wasserstein Natural Gradient.

Michael Arbel, Arthur Gretton, Wuchen Li, Guido Montúfar

Proceedings of the 8th International Conference on Learning Representations, 2020

Synchronizing Probability Measures on Rotations via Optimal Transport.

Tolga Birdal, Michael Arbel, Umut Simsekli, Leonidas J. Guibas

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019

Maximum Mean Discrepancy Gradient Flow.

Michael Arbel, Anna Korba, Adil Salim, Arthur Gretton

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

2018

On gradient regularizers for MMD GANs.

Michael Arbel, Danica J. Sutherland, Mikolaj Binkowski, Arthur Gretton

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Demystifying MMD GANs.

Mikolaj Binkowski, Danica J. Sutherland, Michael Arbel, Arthur Gretton

Proceedings of the 6th International Conference on Learning Representations, 2018

Efficient and principled score estimation with Nyström kernel exponential families.

Danica J. Sutherland, Heiko Strathmann, Michael Arbel, Arthur Gretton

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018

Kernel Conditional Exponential Family.

Michael Arbel, Arthur Gretton

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018

2017

Efficient and principled score estimation.

Danica J. Sutherland, Heiko Strathmann, Michael Arbel, Arthur Gretton

CoRR, 2017