MSB 318: Mathematical Sciences Building, Room 318

Our [Colloquium series](https://sciences.ucf.edu/math/colloquium/) offers a vibrant platform for faculty, students, research scholars, and industry experts to share and exchange ideas, fostering discussion and networking across mathematics, statistics, and data science.

This week, our own professor [Xin Li](https://sciences.ucf.edu/math/person/xin-li/) will present a talk on "Dynamic Inertial Newton Inspired Algorithms And Their Applications to Non-Smooth and Non-Convex Optimizations."

Abstract: Dynamic Inertial Newton (DIN) systems have been used to motivate or explain several accelerated algorithms to solve a wide range of optimization problems. In this presentation, we propose new algorithms inspired by DIN and establish their convergence analysis. Furthermore, we discuss how to apply these algorithms to the applications in deep learning via a smoothing approximation approach. The motivation for our study is two-folds: we give a direct approach to find a critical point of the objective functions, and we want to cover most problems in machine learning whose objective functions are known to be non-smooth and non-convex.

Speaker Bio: Xin Li is a professor of mathematics at UCF, where he has served since 1990, including a decade as department chair. He earned his Ph.D. from the University of South Florida in 1989 under professor E.B. Saff. His research spans approximation theory, orthogonal polynomials, stochastic processes, computer vision, and machine learning, with numerous publications and international presentations. He has led or co-led major research and education projects funded by the NSF, industry, and government agencies, and is affiliated with UCF's Center for Research in Computer Vision. An award-winning educator, Li has guided Ph.D. and master's students and received multiple teaching honors, reflecting his commitment to advancing mathematics and STEM education.