171 citations · 357 across the 21 of their papers we have counts for
22 papers
SLACK: Stable Learning of Augmentations with Cold-start and KL regularization
Juliette Marrie, Michael Arbel, Diane Larlus +1
Data augmentation is known to improve the generalization capabilities of neural networks, provided that the set of transformations is chosen with care, a selection often performed…
Rethinking Gauss-Newton for learning over-parameterized models
Michael Arbel, Romain Menegaux, Pierre Wolinski
This work studies the global convergence and implicit bias of Gauss Newton's (GN) when optimizing over-parameterized one-hidden layer networks in the mean-field regime. We first es…
Maximum Likelihood Learning of Unnormalized Models for Simulation-Based Inference
Pierre Glaser, Michael Arbel, Samo Hromadka +2
We introduce two synthetic likelihood methods for Simulation-Based Inference (SBI), to conduct either amortized or targeted inference from experimental observations when a high-fid…
Non-Convex Bilevel Games with Critical Point Selection Maps
Michael Arbel, Julien Mairal
Bilevel optimization problems involve two nested objectives, where an upper-level objective depends on a solution to a lower-level problem. When the latter is non-convex, multiple…
Continual Repeated Annealed Flow Transport Monte Carlo
Alexander G. D. G. Matthews, Michael Arbel, Danilo J. Rezende +1
We propose Continual Repeated Annealed Flow Transport Monte Carlo (CRAFT), a method that combines a sequential Monte Carlo (SMC) sampler (itself a generalization of Annealed Import…
Amortized Implicit Differentiation for Stochastic Bilevel Optimization
Michael Arbel, Julien Mairal
We study a class of algorithms for solving bilevel optimization problems in both stochastic and deterministic settings when the inner-level objective is strongly convex. Specifical…