Michel Barlaud

collaborators

2 papers

cs.LG2025

A new Linear Time Bi-level $ℓ_{1, \infty}$ projection ; Application to the sparsification of auto-encoders neural networks

Michel Barlaud, Guillaume Perez, Jean-Paul Marmorat

The $ℓ_{1, \infty}$ norm is an efficient-structured projection, but the complexity of the best algorithm is, unfortunately, $O (nm lo g (nm))$ for a matrix $n\t…

cs.LG2024

Multi-level projection with exponential parallel speedup; Application to sparse auto-encoders neural networks

Guillaume Perez, Michel Barlaud

The $ℓ_{1, \infty}$ norm is an efficient structured projection but the complexity of the best algorithm is unfortunately $O (nm lo g (nm))$ for a matrix in $\ma…

A new Linear Time Bi-level ℓ1,∞​ projection ; Application to the sparsification of auto-encoders neural networks

Multi-level projection with exponential parallel speedup; Application to sparse auto-encoders neural networks

A new Linear Time Bi-level $ℓ_{1, \infty}$ projection ; Application to the sparsification of auto-encoders neural networks