95 citations · 203 across the 21 of their papers we have counts for
3 papers · 1 filter
Low-Budget Active Learning through Entropic Optimal Transport
Rim Hajal, Mathieu Besançon, Jérôme Malick
We consider low-budget active learning, which consists of selecting a limited number of points, the coreset, such that a model can be trained to high accuracy on the selection only…
Flexible Differentiable Optimization via Model Transformations
Mathieu Besançon, Joaquim Dias Garcia, Benoît Legat +1
We introduce DiffOpt.jl, a Julia library to differentiate through the solution of optimization problems with respect to arbitrary parameters present in the objective and/or constra…
Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings
Jan Macdonald, Mathieu Besançon, Sebastian Pokutta
We study the effects of constrained optimization formulations and Frank-Wolfe algorithms for obtaining interpretable neural network predictions. Reformulating the Rate-Distortion E…