New Paper Proposes Moment-Guided Optimizer MGO-SC to Stabilize Adam-Style Updates Under Noise
An arXiv paper introduces MGO-SC, a moment-guided optimizer that acts as a consistency gate on Adam-style updates to improve deep learning training under heavy stochasticity and label noise.
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-30 04:00 · arXiv cs.LG
Moment-Guided Optimizers for Noisy Deep Learning: MGO-SC as a Simple Consistency Gate for Adam-Style Updates