AI RESEARCH
Scaling Laws in the Tiny Regime: How Small Models Change Their Mistakes
arXiv CS.LG
•
ArXi:2603.07365v1 Announce Type: new Neural scaling laws describe how model performance improves as a power law with size, but existing work focuses on models above 100M parameters. The sub-20M regime -- where TinyML and edge AI operate -- remains unexamined. We train 90 models (22K--19.8M parameters) across two architectures (plain ConvNet, MobileNetV2) on CIFAR-100, varying width while holding depth and