Lightweight Adaptive ReduNet via Hyperspherical Manifold Learning

The paper introduces LA-ReduNet, a lightweight adaptive version of the ReduNet neural network that uses hyperspherical manifold learning and adaptive step sizes to reduce the number of layers needed for the maximal coding rate reduction (MCR$^2$) objective to stabilize. By refining the layer‑wise update rule, LA-ReduNet achieves comparable classification accuracy while requiring far fewer layers and significantly less parameter storage—about 1/29 of the unfolded ReduNet module under the tested settings.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.