Phase-HDC: Replacing Optimizer History with Gradient Thresholds in Discrete Phase Learning
arXiv:2610.10630v1 Announce Type: new Abstract: Training a compact model often needs far more memory than storing it, because the optimizer keeps its own records of past gradients. For a hyperdimensional classifier whose learned parameters are low-bit angles, which we call a \emph{phase memory}, th…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-09 04:00 · arXiv cs.LG
Phase-HDC: Replacing Optimizer History with Gradient Thresholds in Discrete Phase Learning