Temperon: Full-Time SAM Quality at a Third Less Wall-Clock
This story is from 2026-09-17. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.17575v1 Announce Type: new Abstract: Sharpness-aware minimization (SAM) doubles the cost of every training step, yet its benefit concentrates where training ends. We study where an expensive training mode should be spent and propose Temperon: a plain-SGD explorer for the first 43% of the…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-09-17 04:00 · arXiv cs.LG
Temperon: Full-Time SAM Quality at a Third Less Wall-Clock