Adapt or Forget: Provable Tradeoffs Between Adam and SGD in Nonstationary Optimization
This story is from 2026-09-14. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2605.04269v2 Announce Type: replace Abstract: We provide a theoretical analysis of Adam under non-stationary stochastic objectives, separating two regimes: Euclidean tracking under adaptive strong monotonicity of the Adam-preconditioned mean-gradient operator, and high-probability projected s…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-09-14 04:00 · arXiv stat.ML
Adapt or Forget: Provable Tradeoffs Between Adam and SGD in Nonstationary Optimization