How I learned to stop worrying and love StopGrads: Stationarity, Convergence, and a case study on Flow Map Learning
This story is from 2026-09-16. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.16222v1 Announce Type: new Abstract: Stopgrads are widely used in training machine learning models, but stopgrads can alter the gradient, stationary points and convergence guarantees of the original objective, which can make stopgrad training theoretically ungrounded. We introduce a stop…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-09-16 04:00 · arXiv cs.LG
How I learned to stop worrying and love StopGrads: Stationarity, Convergence, and a case study on Flow Map Learning