arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.04669cs.LG
收藏

通过不精确学习实现领域泛化

Domain Generalisation via Imprecise Learning

CISPA Helmholtz Center for Information Security(CISPA亥姆霍兹信息安全中心);University of Oxford(牛津大学)

Anurag Singh, Siu Lun Chau, Shahine Bouabid, Krikamol Muandet

AI总结:

针对分布外泛化中因学习者和操作者分离导致的泛化策略选择难题,提出不精确领域泛化框架,在训练时优化连续策略谱,部署时由操作者指定偏好,理论与实验均证明其有效性。

摘要:

分布外(OOD)泛化具有挑战性,因为它不仅涉及从经验数据中学习,还涉及在各种泛化概念之间做出决策,例如优化平均情况风险、最坏情况风险或其间的插值。虽然原则上这一选择应由模型操作者(如医生)做出,但在训练时这些信息可能并不总是可用。机器学习者和模型操作者之间的制度分离,导致机器学习者在面临部署不确定性时,随意承诺特定的泛化策略。我们引入了不精确领域泛化框架来缓解这一问题,其特点是不精确风险优化,允许学习者在训练期间通过针对连续泛化策略谱进行优化来保持不精确性,以及一个允许操作者在部署时指定其泛化偏好的模型框架。在理论和实证证据的支持下,我们的工作展示了将不精确性整合到领域泛化中的益处。

英文摘要:

Out-of-distribution (OOD) generalisation is challenging because it involves not only learning from empirical data, but also deciding among various notions of generalisation, e.g., optimising the average-case risk, worst-case risk, or interpolations thereof. While this choice should in principle be made by the model operator like medical doctors, this information might not always be available at training time. The institutional separation between machine learners and model operators leads to arbitrary commitments to specific generalisation strategies by machine learners due to these deployment uncertainties. We introduce the Imprecise Domain Generalisation framework to mitigate this, featuring an imprecise risk optimisation that allows learners to stay imprecise by optimising against a continuous spectrum of generalisation strategies during training, and a model framework that allows operators to specify their generalisation preference at deployment. Supported by both theoretical and empirical evidence, our work showcases the benefits of integrating imprecision into domain generalisation.

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。

↑