260 citations · 836 across the 69 of their papers we have counts for
8 papers · 1 filter
A Bregman Method for Structure Learning on Sparse Directed Acyclic Graphs
Manon Romain, Alexandre d'Aspremont
We develop a Bregman proximal gradient method for structure learning on linear structural causal models. While the problem is non-convex, has high curvature and is in fact NP-hard,…
Convergence of Constrained Anderson Acceleration
Mathieu Barré, Adrien Taylor, Alexandre d'Aspremont
We prove non asymptotic linear convergence rates for the constrained Anderson acceleration extrapolation scheme. These guarantees come from new upper bounds on the constrained Cheb…
Averaging Atmospheric Gas Concentration Data using Wasserstein Barycenters
Mathieu Barré, Clément Giron, Matthieu Mazzolini +1
Hyperspectral satellite images report greenhouse gas concentrations worldwide on a daily basis. While taking simple averages of these images over time produces a rough estimate of…
FANOK: Knockoffs in Linear Time
Armin Askari, Quentin Rebjock, Alexandre d'Aspremont +1
We describe a series of algorithms that efficiently implement Gaussian model-X knockoffs to control the false discovery rate on large scale feature selection problems. Identifying…
A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention
Grégoire Mialon, Dexiong Chen, Alexandre d'Aspremont +1
We address the problem of learning on sets of features, motivated by the need of performing pooling operations in long biological sequences of varying sizes, with long-range depend…
Projection-Free Optimization on Uniformly Convex Sets
Thomas Kerdreux, Alexandre d'Aspremont, Sebastian Pokutta
The Frank-Wolfe method solves smooth constrained convex optimization problems at a generic sublinear rate of , and it (or its variants) enjoys accelerated converg…