First-Passage Prediction of Grokking Delay: ACalibrated Law under AdamW with Causal Validation
The article presents a quantitative prediction of grokking delay under the AdamW optimization algorithm. It introduces a closed-form law for predicting this delay based on various parameters and validates it through empirical testing. The findings suggest that while the law is effective for certain architectures, its applicability to natural-language models remains uncertain.
- ▪The study derives a closed-form law for grokking delay under AdamW, predicting delays with a mean absolute percentage error of 17.7%.
- ▪Calibrating specific parameters allows for accurate predictions across different architectures, with a maximum coefficient of variation of 15%.
- ▪Causal interventions that alter weight decay significantly affect grokking outcomes, indicating the importance of norm separation and angular reachability.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.18845 |
| Publication time | Wed, 20 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-20T04:04:59.484Z |
| Last seen | 2026-05-20T04:04:59.484Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | pR_sLG3_tv15 |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Machine Learning arXiv:2605.18845 (cs) [Submitted on 13 May 2026] Title:First-Passage Prediction of Grokking Delay: ACalibrated Law under AdamW with Causal Validation Authors:Truong Xuan Khanh, Truong Quynh Hoa, Luu Duc Trung, Phan Thanh Duc View a PDF of the paper titled First-Passage Prediction of Grokking Delay: ACalibrated Law under AdamW with Causal Validation, by Truong Xuan Khanh and 3 other authors View PDF HTML (experimental) Abstract:We give the first quantitative prediction of grokking delay under AdamW.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
