A0587
Title: Learning theory of spectral algorithms under covariate shift
Authors: Zheng-Chu Guo - Zhejiang University (China) [presenting]
Abstract: In machine learning, it is commonly assumed that the training and test samples are drawn from the same underlying distribution. However, this assumption may not always hold true in practice. A scenario is delved into where the distribution of the input variables (also known as covariates) differs between the training and test phases. This situation is referred to as a covariate shift. To address the challenges posed by covariate shift, various techniques have been developed, such as importance weighting, domain adaptation, and reweighting methods. The focus is on the weighted spectral algorithm. Under mild conditions imposed on the weights, it is demonstrated that this algorithm achieves satisfactory convergence rates.
