Beyond Quadratic Loss: The Stability Phase Diagram of Adam
This story is from 2026-09-17. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.18314v1 Announce Type: cross Abstract: Loss spikes are recurrent instabilities in neural-network training and can arise from multiple mechanisms. For Adam in particular, macroscopic loss spikes have been linked to optimizer dynamics, yet how its two momentum timescales govern them remain…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-09-17 04:00 · arXiv stat.ML
Beyond Quadratic Loss: The Stability Phase Diagram of Adam