Papers › A new Linear Time Bi-level ℓ_(1,∞) projection ; Application to the sparsification of...

A new Linear Time Bi-level ℓ_(1,∞) projection ; Application to the sparsification of auto-encoders neural networks

23 Jul 2024arXiv:2407.16293archive 2025-07-28

Michel Barlaud, Guillaume Perez, Jean-Paul Marmorat

The ℓ_(1,∞) norm is an efficient-structured projection, but the complexity of the best algorithm is, unfortunately, 𝒪(n m log(n m)) for a matrix n×m.\\ In this paper, we propose a new bi-level projection method, for which we show that the time complexity for the ℓ_(1,∞) norm is only 𝒪(n m ) for a matrix n×m. Moreover, we provide a new ℓ_(1,∞) identity with mathematical proof and experimental validation. Experiments show that our bi-level ℓ_(1,∞) projection is $2.5$ times faster than the actual fastest algorithm and provides the best sparsity while keeping the same accuracy in classification applications.

PaperPDFCode

Code

MichelBarlaud/SAE-Supervised-Autoencoder-Omics officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections