He Chenxuan, a doctoral student at the Institute of Statistics and Big Data, Renmin University of China (RUC), is the first author of a paper titled "A Goodness-of-Fit Assessment for General Learning Procedures in High Dimensions", which has been accepted for publication by the prestigious Journal of the American Statistical Association (JASA).

Screenshot of the paper titled "A Goodness-of-Fit Assessment for General Learning Procedures in High Dimensions". [Photo/ruc.edu.cn]

Abstract: Black-box learners have demonstrated remarkable success across various fields due to their high predictive accuracy. However, the complexity of their learning procedures poses significant challenges in evaluating whether a given learner has achieved optimal performance on datasets with unknown data-generating mechanisms. This paper proposes a general goodness-of-fit test for assessing different learning procedures involving high-dimensional predictors, encompassing methods from classical linear regression to advanced neural networks. The proposed goodness-of-fit test leverages data-splitting, using the test set to evaluate the black-box learner trained on the training set. By examining the cumulative covariance of the residuals, the method can effectively handle high-dimensional predictors. Extensive simulations and three real data analyses validate the effectiveness of the proposed method. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work.

About the authors:

He Chenxuan, a 2022 doctoral student at RUC's Institute of Statistics and Big Data. His research focuses on statistical testing, nonparametric statistics, machine learning and deep learning.

Chen Canyi, a 2023 graduate of RUC's Institute of Statistics and Big Data and currently a postdoctoral researcher at the University of Michigan. Chen's research focuses on distributed computing, model diagnostics and mediation effects.

Zhu Liping, a distinguished professor and dean of the Institute of Statistics and Big Data at RUC, supervising doctoral students and leading research initiatives in the field.