arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.07005cs.DScs.LG
收藏

粗粒度与细粒度模型在存在分布偏移学习中的等价性

Equivalence of Coarse and Fine-Grained Models for Learning with Distribution Shift

UT Austin(得克萨斯大学);Columbia University(哥伦比亚大学)

Adam R. Klivans, Shyamal Patel, Konstantinos Stavropoulos, Arsen Vasilyan

AI总结:

本文探讨了在无分布假设下,粗粒度与细粒度学习模型的等价性,证明了通过黑盒减少将PQ学习转换为TDS学习的效率,并展示了通过成员查询可绕过硬度结果,实现半空间的分布自由PQ可学习性。

摘要:

最近关于能保证高效学习存在分布偏移的算法研究,集中在两种模型上:PQ学习(Goldwasser等人,2020)和TDS学习(Klivans等人,2024)。TDS学习算法允许在检测到分布偏移时完全拒绝测试集,而PQ学习者只能根据个体点是否被认为是分布外来拒绝。我们的主要结果是在无分布假设下,这两种模型之间存在令人惊讶的等价性。具体来说,我们为任何布尔概念类给出了高效的黑盒减少方法,将PQ学习转换为TDS学习。这种等价性意味着首次在无分布假设下对基本类如半空间的TDS学习的难度结果。我们等价性的主要技术贡献是通过分支程序提升TDS学习者拒绝目标域的弱区分能力。我们还展示,给学习器提供成员查询访问可以绕过这些难度结果,并允许高效地分布自由地学习半空间。我们的算法通过迭代地从训练数据上应用连续的Forster变换来恢复大边距分离器。

英文摘要:

Recent work on provably efficient algorithms for learning with distribution shift has focused on two models: PQ learning (Goldwasser et al. (2020)) and TDS learning (Klivans et al. (2024)). Algorithms for TDS learning are allowed to reject a test set entirely if distribution shift is detected. In contrast, PQ learners may only reject points that are deemed out-of-distribution on an individual basis. Our main result is a surprising equivalence between these two models in the distribution-free setting. In particular, we give an efficient black-box reduction from PQ learning to TDS learning for any Boolean concept class. This equivalence implies the first hardness results for distribution-free TDS learning of basic classes such as halfspaces. The main technical contribution underlying our equivalence is a method for boosting, via branching programs, the weak distinguishing power of TDS learners that have rejected the target domain. We also show that giving a learner access to membership queries sidesteps these hardness results and allows for efficient, distribution-free PQ learnability of halfspaces. Our algorithm iteratively recovers large-margin separators obtained by applying successive Forster transforms on the training data.

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。

↑