金年会jinnianhuicom学术报告
Efficiency of Smooth Approximation Methods for Weakly Convex Optimization
邓琪
（上海交通大学）
报告时间：2026年1月19日 星期一 下午16：30-17：30
报告地点：沙河校区E806
报告摘要：Standard complexity analyses for weakly convex optimization rely on the Moreau envelope technique proposed by Davis and Drusvyatskiy (2019). The main insight is that nonsmooth algorithms, such as proximal subgradient, proximal point, and their stochastic variants, implicitly minimize a smooth surrogate function induced by the Moreau envelope. Meanwhile, explicit smoothing, which directly minimizes a smooth approximation of the objective, has long been recognized as an efficient strategy for nonsmooth optimization. In this paper, we generalize the notion of smoothable functions, originally introduced by Nesterov (2005) and later expanded by Beck and Teboulle (2012) for nonsmooth convex optimization. This generalization provides a unified viewpoint on several important smoothing techniques for weakly convex optimization, including Nesterov-type smoothing and Moreau envelope smoothing. Our theory yields a framework for designing smooth approximation algorithms for both deterministic and stochastic weakly convex problems with provable complexity guarantees. Furthermore, our theory extends to the smooth approximation of non-Lipschitz functions, allowing for complexity analysis even when global Lipschitz continuity does not hold.
报告人简介：邓琪，现任上海交通大学安泰经济与管理学院副教授，此前在上海财经大学信息管理与工程学院工作，分别担任助理教授和副教授。分别于美国佛罗里达大学和上海交通大学获得计算机专业博士和学士学位。主要研究兴趣包括连续优化算法设计、复杂度分析和机器学习中的应用。近年来的研究成果发表在 MP, IJOC, MOR, POMS, NeurIPS, ICML等优化与机器学习领域的期刊和会议上。现主持国家和上海市自科面上项目，参与国家自科重大项目。
邀请人：谢家新
