Grokking signatures in prior MNIST examples vanish under standard training, NeurIPS paper finds
s_y_chung · x · 2026-11-11
(thread tail) The same measurement framework also flags spurious generalization dynamics: a previously reported MNIST grokking example and a label-noise double descent example stem from degraded representations and a misaligned readout under non-standard recipes. The signatures disappear under standard training — suggesting some reported grokking/double descent cases are training-recipe artifacts rather than universal phenomena.
Related event: "Two Speeds of Learning" Paper Unifies Grokking and Double Descent(5 posts)→
More from Research
- Prism capability extraction: specialists carved from Qwen 27B at <20% memory match full model — tokenbender · 2026-11-11
- Data Colada Flags Fraud in Fifth Francesca Gino Paper, No Forensics Needed — danielrock · 2026-11-11
- Fable 5.2 tops GDPx chip-design benchmark, but task authors see zero gains — ycombinator · 2026-11-11
- Fortnow asks Claude about complexity in the Aronson-Ambainis proof: Promise-BQP-complete — fortnow · 2026-11-11
- Backdooring AI agents by reprogramming fewer than 10 dormant neurons — no training needed — DimitrisPapail · 2026-11-11
- Duke and Princeton paper: 10 small parallel agent teams beat best-of-N and one giant team — rohanpaul_ai · 2026-11-11