学术报告(郭正初 2024.9.20)
Learning theory of spectral algorithms under covariate shift
摘要: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. In this talk, we delve into a scenario where the distribution of the input variables (also known as covariates), differs between the training and test phases. This situation is referred to as covariate shift. To address the challenges posed by covariate shift, various techniques have been developed, such as importance weighting, domain adaptation, and reweighting methods. In this talk, we specifically focus on the weighted spectral algorithm. Under mild conditions imposed on the weights, we demonstrate that this algorithm achieves satisfactory convergence rates. This talk is based on joint work with Prof. Jun Fan and Prof. Lei Shi.