Metraipolis › archive › dc_d3e89ee8b2d3
Does Random Search Discover Task Experts? Revisiting Neural Thickets — arXiv:2611.01262
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01262
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:24:35.686Z
- SHA-256 of the archived text
126a8d97f5829b414f59e524f440d6ed694a5fc1d34840255adfe466af27292a- Stable URL of this page
https://metraipolis.com/documento/dc_d3e89ee8b2d3
How to cite
Does Random Search Discover Task Experts? Revisiting Neural Thickets — arXiv:2611.01262 — arXiv (en), https://arxiv.org/abs/2611.01262 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d3e89ee8b2d3 (Metraipolis archive dc_d3e89ee8b2d3, sha256 126a8d97f5829b414f59e524f440d6ed694a5fc1d34840255adfe466af27292a)
BibTeX
@misc{dcd3e89ee8b2d3,
title = {Does Random Search Discover Task Experts? Revisiting Neural Thickets — arXiv:2611.01262},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01262},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d3e89ee8b2d3; sha256 126a8d97f5829b414f59e524f440d6ed694a5fc1d34840255adfe466af27292a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01262. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Pretrained models are typically viewed as generalists, requiring bespoke post-training to achieve task-specific expertise. Gan & Isola (2026) recently proposed a striking alternative: that pretrained models lie in a dense neural thicket of task specialists, which can be surfaced with simple Gaussian weight perturbations. We examine this neural thicket of task-specific experts and identify several key findings that question this perspective. First, we find that the apparent lift of the best-of-N selected perturbation decays quickly with selection-set size m, strongly suggesting overfitting to the selection questions. In fact, for 10 of the 12 model-task pairs we study, a simple null model of pure selection noise predicts more than 75 percent of the top expert's reward lift. Second, the top experts' advantage often vanishes on held-out questions or remains within the run-to-run variability of the unperturbed pretrained model. Third, we find that majority voting over the top-K selected perturbations, termed RandOpt(N, K) by Gan & Isola (2026), is often matched or outperformed by majority voting over K samples from the base model. Overall, our results suggest that random weight perturbations may be ineffective at uncovering task experts around pretrained models, and that task adaptation requires more sophistication than random search. Code and artifacts are available at this http URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.01262 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T18:10:08.026Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).