Papers › Convex Geometry of ReLU-layers, Injectivity on the Ball and Local Reconstruction

Convex Geometry of ReLU-layers, Injectivity on the Ball and Local Reconstruction

18 Jul 2023arXiv:2307.09672archive 2025-07-28

Daniel Haider, Martin Ehler, Peter Balazs

The paper uses a frame-theoretic setting to study the injectivity of a ReLU-layer on the closed ball of ℝⁿ and its non-negative part. In particular, the interplay between the radius of the ball and the bias vector is emphasized. Together with a perspective from convex geometry, this leads to a computationally feasible method of verifying the injectivity of a ReLU-layer under reasonable restrictions in terms of an upper bound of the bias vector. Explicit reconstruction formulas are provided, inspired by the duality concept from frame theory. All this gives rise to the possibility of quantifying the invertibility of a ReLU-layer and a concrete reconstruction algorithm for any input vector on the ball.

PaperPDFCode

Code

danedane-haider/alpha-rectifying-frames officialmentioned in papermentioned 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