arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.04724cs.LGmath.STstat.MLstat.TH
收藏

基于函数回归的域泛化

Domain Generalization by Functional Regression

Johannes Kepler University Linz(林茨约翰·开普勒大学);Austrian Academy of Sciences(奥地利科学院)

Markus Holzleitner, Sergei V. Pereverzyev, Werner Zellinger

AI总结:

该研究将域泛化转化为函数回归问题,提出一种学习从输入边缘分布到输出条件分布的线性算子的新算法,支持构建源分布依赖的再生核希尔伯特空间,满足理想风险的有限样本误差界,且已公开实现代码。

摘要:

域泛化问题是指:给定来自不同源分布的数据,学习一个模型,使其能在仅通过无标签样本观测到的新目标分布上具备良好的泛化能力。本文将域泛化作为函数回归问题展开研究,基于这一思路提出了一种新算法,用于学习从输入的边缘分布到给定输入下输出的对应条件分布的线性算子。该算法支持构建依赖源分布的再生核希尔伯特空间(reproducing kernel Hilbert spaces)用于预测,并且满足理想风险的有限样本误差界。相关数值实现代码和源代码已公开。

英文摘要:

The problem of domain generalization is to learn, given data from different source distributions, a model that can be expected to generalize well on new target distributions which are only seen through unlabeled samples. In this paper, we study domain generalization as a problem of functional regression. Our concept leads to a new algorithm for learning a linear operator from marginal distributions of inputs to the corresponding conditional distributions of outputs given inputs. Our algorithm allows a source distribution-dependent construction of reproducing kernel Hilbert spaces for prediction, and, satisfies finite sample error bounds for the idealized risk. Numerical implementations and source code are available.

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。

↑