报告题目：New Adaptive Gradient Methods for Convex and Nonconvex Optimization

报告人：杨俊锋 教授

报告时间：2026年5月20日上午10:00

报告地点：数统学院402

邀请人：刘勇进

邀请单位：福州大学数学与统计学院

报告摘要：Two-phase flow systems exhibit rich interfacial dynamics, where droplet and bubble shape evolution is governed by a delicate balance between driving forces and dissipative mechanisms. Capturing these dynamics with reduced computational cost, while preserving physical fidelity, remains a major challenge. In this talk, I present recent progress on model reduction for interfacial flows based on the Onsager variational principle. The first part focuses on droplet motion on inclined substrates, where a data-driven reduced-order model integrates Onsager’s framework with Functional Principal Component Analysis, enabling accurate prediction of complex morphologies beyond classical continuum descriptions. The second part addresses bubble dynamics in Hele-Shaw cells, where generalized Onsager modeling reveals size-dependent shape transitions and highlights the critical role of Bretherton-type boundary dissipation. Together, these studies demonstrate how Onsager-based approaches provide a systematic pathway to efficient, predictive, and physically consistent reduced models for two-phase flow problems.

报告人简介：杨俊锋，南京大学数学学院教授、博导；河北省邢台市威县人，2003年在河北师范大学数学系获学士学位，2009年在南京大学数学系获博士学位，先后在中国科学院数学与系统科学研究院、Rice大学联合培养；2009年7月起在南京大学数学系工作至今，期间先后在新加坡国立大学、香港中文大学等访学；主要从事数学优化计算方法及其应用研究，代表作发表在Math. Comput.、IMAJNA、Math. Oper. Res.、SIOPT、SISC、SIIMS、IJOO、JSC、Inverse Prob.、IEEE J Sel Top Signal Process等杂志，设计完成图像复原代码包FTVd、压缩感知解码包YALL1等；入选教育部新世纪优秀人才支持计划、获中国运筹学会青年科技奖、2020至2025年连续6次入选爱思唯尔中国高被引学者等，先后主持国家自然科学基金青年、面上、优青等项目。现担任中国运筹学会理事、江苏省运筹学会监事长、民建江苏省委员会大数据与人工智能委员会委员等；担任Applied Set-Valued Analysis and Optimization (ASVAO)、Numerical Algebra, Control and Optimization (NACO)、Statistics, Optimization and Information Computing (SOIC) 、《计算数学》编委，Optimization and Engineering客座编委等。