New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions
A new paper presents insights into variance reduction in zero-order hard-thresholding algorithms. The proposed method addresses limitations in existing algorithms by improving convergence rates and applicability. This research could enhance performance in machine learning tasks involving sparsity constraints.
- ▪The paper introduces a generalized variance reduced zero-order hard-thresholding algorithm.
- ▪This new approach mitigates conflicts between zero-order gradients and hard-thresholding operators.
- ▪The theoretical results indicate improved convergence rates compared to the existing SZOHT algorithm.
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/2605.18035 |
| Publication time | Tue, 19 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-19T04:04:57.272Z |
| Last seen | 2026-05-19T04:04:57.272Z |
| 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 | 33ASbwqKSfPy |
| 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 > Artificial Intelligence arXiv:2605.18035 (cs) [Submitted on 18 May 2026] Title:New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions Authors:Xinzhe Yuan (1), William de Vazelhes (2), Bin Gu (2 and 3), Huan Xiong (1 and 2) ((1) Harbin Institute of Technology, (2) Mohamed bin Zayed University of Artificial Intelligence, (3) Jilin University) View a PDF of the paper titled New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions, by Xinzhe Yuan (1) and 5 other authors View PDF HTML (experimental) Abstract:Hard-thresholding is an important type of algorithm in machine learning that is used to solve $\ell_0$ constrained optimization problems.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
