G. Perez

activity

20152023

most citedRelations between MDDs and Tuples and Dynamic Modifications of MDDs based constraints

2 citations · 3 across the 5 of their papers we have counts for

collaborators

Showing cs.LGShow all

3 papers · 1 filter

cs.LG2023

Near-Linear Time Projection onto the $ℓ_{1, \infty}$ Ball; Application to Sparse Autoencoders

Guillaume Perez, Laurent Condat, Michel Barlaud

Looking for sparsity is nowadays crucial to speed up the training of large-scale neural networks. Projections onto the $ℓ_{1, 2}$ and $ℓ_{1, \infty}$ are among the most efficie…

cs.LG2021

Constrained Machine Learning: The Bagel Framework

Guillaume Perez, Sebastian Ament, Carla Gomes +1

Machine learning models are widely used for real-world applications, such as document analysis and vision. Constrained machine learning problems are problems where learned models h…

cs.LG2020★ 1 cited

Efficient Projection Algorithms onto the Weighted l1 Ball

Guillaume Perez, Sebastian Ament, Carla Gomes +1

Projected gradient descent has been proved efficient in many optimization and machine learning problems. The weighted $ℓ_{1}$ ball has been shown effective in sparse system identi…

Near-Linear Time Projection onto the ℓ1,∞​ Ball; Application to Sparse Autoencoders

Constrained Machine Learning: The Bagel Framework

Efficient Projection Algorithms onto the Weighted l1 Ball

Near-Linear Time Projection onto the $ℓ_{1, \infty}$ Ball; Application to Sparse Autoencoders