Linear mode connectivity appears on test loss but not train loss, notes researcher Arohan

_arohan_ · x · 2026-09-28

Researcher arohan calls linear mode connectivity one of the most underrated features of training neural nets, recalling his 4-year-old finding that it appears on test loss but not on train loss — something he found mind-blowing at the time.

Updates from @stanislavfort's colab using DistributedShampoo (near-zero train loss): train/test loss of 0.0002/0.314 vs baseline 0.350/0.333, and train/test accuracy of 0.999/0.982 — showing the phenomenon persists even in the low-train-loss regime.

Original post →

More from Research

Research channel →