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 2401.11554math.STstat.TH
收藏

协变量偏移下的迁移学习:重尾设计的局部 $k$-近邻回归

Transfer Learning under Covariate Shift: Local $k$-Nearest Neighbours Regression with Heavy-Tailed Design

Petr Zamolodtchikov, Hanyuan Hang

AI总结:

针对无界支撑与重尾目标分布下的协变量偏移迁移学习,提出密度比指数与按样本边缘似然调节近邻数的局部 k-近邻回归器,并证明其更快收敛速率。

摘要:

协变量偏移是一种常见的迁移学习情形,其中输入变量的边缘分布在源数据与目标数据之间存在差异,而输出变量的条件分布保持一致。现有用于描述边缘分布之间差异的概念在处理无界支撑情形时存在局限,尤其是在目标分布具有更重尾部时。为克服这些挑战,我们引入一个称为密度比指数的新概念,用于量化协变量偏移下边缘分布尾部的相对衰减率。此外,我们提出用于迁移学习的局部 k-近邻回归器,该回归器根据每个测试样本的边缘似然来调整近邻数量。在理论方面,我们建立了在目标域具有和不具有监督信息两种情况下的收敛速率。这些速率表明,当密度比指数满足特定条件时,我们的估计量能够获得更快的收敛速率,这凸显了利用密度估计为每个测试样本确定不同近邻数量的优势。我们的贡献增强了对协变量偏移下迁移学习的理解与适用性,尤其是在无界支撑和重尾分布情形中。

英文摘要:

Covariate shift is a common transfer learning scenario where the marginal distributions of input variables vary between source and target data while the conditional distribution of the output variable remains consistent. The existing notions describing differences between marginal distributions face limitations in handling scenarios with unbounded support, particularly when the target distribution has a heavier tail. To overcome these challenges, we introduce a new concept called density ratio exponent to quantify the relative decay rates of marginal distributions' tails under covariate shift. Furthermore, we propose the local k-nearest neighbour regressor for transfer learning, which adapts the number of nearest neighbours based on the marginal likelihood of each test sample. From a theoretical perspective, convergence rates with and without supervision information on the target domain are established. Those rates indicate that our estimator achieves faster convergence rates when the density ratio exponent satisfies certain conditions, highlighting the benefits of using density estimation for determining different numbers of nearest neighbours for each test sample. Our contributions enhance the understanding and applicability of transfer learning under covariate shift, especially in scenarios with unbounded support and heavy-tailed distributions.

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。

↑