The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?
The paper discusses the advantages of Gated Linear Units (GLU) over non-gated structures in machine learning models. It highlights how GLU reshapes the neural tangent kernel spectrum, resulting in faster convergence during training. The findings suggest that while GLU improves optimization speed, it does not significantly reduce the generalization gap across various models.
- ▪Gated Linear Units (GLU) outperform non-gated counterparts in large language models.
- ▪The analysis reveals that GLU leads to a smaller condition number and a compact eigenvalue distribution.
- ▪GLU primarily accelerates optimization rather than reducing the generalization gap.
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/2605.20749 |
| Publication time | Fri, 22 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-22T04:02:00.009Z |
| Last seen | 2026-05-22T04:02:00.009Z |
| 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 | -l4lunBzjiOh |
| 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:2605.20749 (cs) [Submitted on 20 May 2026] Title:The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure? Authors:Xingyu Lyu, Qianqian Xu, Zhiyong Yang, Peisong Wen, Qingming Huang View a PDF of the paper titled The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?, by Xingyu Lyu and 4 other authors View PDF HTML (experimental) Abstract:Gated Linear Units (GLU) and their variants are widely adopted in modern open-source large language model architectures and consistently outperform their non-gated counterparts, yet the underlying reasons for this advantage remain unclear. In this work, we study GLU by analyzing two-layer networks in the neural tangent kernel (NTK) regime.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
