arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.15898cs.LGcs.AI
收藏

直推式主动学习:理论与应用

Transductive Active Learning: Theory and Applications

Jonas Hübotter, Bhavya Sukhija, Lenart Treven, Yarden As, Andreas Krause

AI总结:

本文提出直推式主动学习框架,在采样区域受限但预测目标可在外部的场景下,证明自适应采样决策规则一致收敛到最小不确定性,并在大型网络主动微调与安全贝叶斯优化中取得最先进性能。

摘要:

我们研究将经典主动学习推广到具有具体预测目标的现实场景,其中采样仅限于域中可访问的区域,而预测目标可能位于该区域之外。我们分析了一类自适应采样以最小化预测目标不确定性的决策规则。我们首次证明,在一般正则性假设下,此类决策规则一致收敛到可从可访问数据中获得的最小可能不确定性。我们在两个关键应用中展示了它们强大的样本效率:大型神经网络的主动微调和安全贝叶斯优化,在这两项任务中它们均取得了最先进的性能。

英文摘要:

We study a generalization of classical active learning to real-world settings with concrete prediction targets where sampling is restricted to an accessible region of the domain, while prediction targets may lie outside this region. We analyze a family of decision rules that sample adaptively to minimize uncertainty about prediction targets. We are the first to show, under general regularity assumptions, that such decision rules converge uniformly to the smallest possible uncertainty obtainable from the accessible data. We demonstrate their strong sample efficiency in two key applications: active fine-tuning of large neural networks and safe Bayesian optimization, where they achieve state-of-the-art performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑