Phase-HDC: Replacing Optimizer History with Gradient Thresholds in Discrete Phase Learning
Ahmed Nebli. arXiv:2610.10630, October 2026.
TLDRA learned classifier stores each parameter as a 6-bit dial. At every update a dial turns one notch against its gradient, but only when the gradient is larger than a fixed write cost, so no optimiser history is kept at all. On a controlled digits benchmark it reaches 92.4% test accuracy against 91.2% for Adam with 6-bit moments, with three times less training state (4.27 KiB against 12.80 KiB). The accuracy gap is within noise, so the result shows that the idea works, not that it beats Adam.
Read on arXiv · Code · Try it in the playground