Metraipolis › archive › dc_98efac461516
Low-Budget Active Learning through Entropic Optimal Transport — arXiv:2610.01199
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.01199
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T16:01:29.895Z
- SHA-256 of the archived text
c278cd4bb54166c752a9389268af37fc1f130103d250e33aaad6f2b15a1eef97- Stable URL of this page
https://metraipolis.com/documento/dc_98efac461516
How to cite
Low-Budget Active Learning through Entropic Optimal Transport — arXiv:2610.01199 — arXiv (en), https://arxiv.org/abs/2610.01199 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_98efac461516 (Metraipolis archive dc_98efac461516, sha256 c278cd4bb54166c752a9389268af37fc1f130103d250e33aaad6f2b15a1eef97)
BibTeX
@misc{dc98efac461516,
title = {Low-Budget Active Learning through Entropic Optimal Transport — arXiv:2610.01199},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.01199},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_98efac461516; sha256 c278cd4bb54166c752a9389268af37fc1f130103d250e33aaad6f2b15a1eef97},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01199. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We consider low-budget active learning, which consists of selecting a limited number of points, the coreset, such that a model can be trained to high accuracy on the selection only. This problem is particularly relevant in contexts where labeling requires costly expert intervention, as in medical applications. We leverage features extracted from a pretrained self-supervised model to represent the data, and perform coreset selection directly in this feature space. In this paper, we use entropic optimal transport, specifically the Sinkhorn divergence, as the coreset selection criterion, which first allows us to get dimension-free sample complexity results, and second admits computationally efficient gradient evaluations. This opens the way to using gradient-based algorithms to rapidly compute solution candidates, further improved by a swap-based local search, with guarantees on the solution quality. Experiments on image benchmarks and medical datasets show that our method outperforms state-of-the-art heuristics in low-budget settings. Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-10-02 in math.OC). Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC). Pagina del lavoro: https://arxiv.org/abs/2610.01199 — 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 2026-10-06T15:14:57.997Z dalla pagina https://arxiv.org/catchup/math.OC/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).