统计与数据科学系系列学术报告之五百二十四期

时    间：2026年10月16日（星期五）10:00-11:00

主持人：复旦大学 管理学院 统计与数据科学系 郁文 教授

地    点：史带楼302室

报  告 人：范剑青 教授

          普林斯顿大学

题   目：SMART Fine-tuning Factor Augmented Neural Lasso

摘   要：Fine-tuning is a widely used strategy for adapting pre-trained models to new tasks, yet its methodology and theoretical properties in high-dimensional nonparametric settings with variable selection have not yet been developed. We propose a source-model-augmented residual tuning (SMART) framework, which incorporates the pre-trained source model into the target learner and estimates only the residual target-specific component. The approach is widely applicable, from parametric and sparse models to neural networks and blackbox machine learning models. We focus on the development of fine-tuning factor-augmented neural Lasso, resulting in SMART-FAN-Lasso. This transfer-learning framework for high-dimensional nonparametric regression with variable selection simultaneously handles covariate and posterior shifts. We use a low-rank factor structure to manage high-dimensional dependent covariates and a residual tuning decomposition in which the target function is expressed as a function of the source model and other target-specific variables, thereby reducing the effective complexity of the target task. We derive minimax-optimal excess risk bounds for SMART-FAN-Lasso, characterizing the precise conditions, in terms of relative sample sizes and function complexities, under which fine-tuning yields statistical acceleration over single-task learning. Extensive numerical experiments across diverse covariate- and posterior-shift scenarios demonstrate that SMART-FAN-Lasso consistently outperforms standard baselines and achieves near-oracle performance even under severe target sample size constraints, empirically validating the derived rates.

个人简介：范剑青教授是美国普林斯顿大学金融讲座教授，运筹与金融工程教授和前系主任，美国国家科学院院士, 比利时皇家科学院外籍院士,“中央研究院”院士, 复旦大学大数据学院、大数据研究院创院院长, 国际数理统计学会和泛华统计学会前主席。他荣获 2000 年度的 COPSS总统奖，2007 年荣获“晨兴华人数学家大会应用数学金奖”，2013 年获泛华统计学会的“许宝禄奖”，2014年荣获英国皇家统计学会的“Guy 奖”的银质奖章，2018年美国统计学会的Noether杰出学者奖，2021年国际数理统计学Le Cam奖，2024科学前沿奖，和2025年国际数理统计最高奖Wald 奖。此外，他还是美国科学促进会(AAAS)、美国统计学会 (ASA)、国际数理统计学会 (IMS)，计量金融学会（SOFIE）的 会士，以及国际顶尖统计期刊 《Journal of American Statistical Association》主编，《Management Science》金融部门的主编，《Annals of Statistics》，《Probability Theory and Related Fields》,《Journal of Econometrics》，《Journal of Business and Economics》等的前主编等。他的主要研究领域包括高维统计，人工智能，机器学习、计量金融、生物信息等, 并在这些领域著有4本专著, 三百多篇文章，引领这些领域的研究，是高被用的学者。