A Learnability Gap, Not a Capacity Gap: 353 Parameters vs a 3-Parameter Heuristic

A Learnability Gap, Not a Capacity Gap What 208 benchmark runs and four experiments in a single file showed me about online learning for browser frame scheduling. Haksung Lee | 2026-04 TL;DR. A 353-parameter MLP with online SGD fails to match a 3-parameter EMA heuristic at browser frame scheduling, by ~10 pp jank rate on ramping workloads. Capacity is sufficient offline distillation reaches 98% imitation with a sharp decision boundary at the right threshold. The failure is geometric: online SGD