3 papers
cs.CV2026
PEPS: Positional Encoding Projected Sampling -- Extended
Guillaume Perez, Janarbek Matai, Takahiro Harada
Implicit neural representations (INRs) are increasingly being used as tools to map coordinates to signals, encompassing applications from neural fields to texture compression, shap…
cs.LG2025
A new Linear Time Bi-level projection ; Application to the sparsification of auto-encoders neural networks
Michel Barlaud, Guillaume Perez, Jean-Paul Marmorat
The norm is an efficient-structured projection, but the complexity of the best algorithm is, unfortunately, 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 norm is an efficient structured projection but the complexity of the best algorithm is unfortunately for a matrix in $\ma…