March 10, 2023, ESB 2001

Optimization has always played a key role in solving problems in data science, and the engagement between these areas continues to grow. In this talk, we discuss how formulation and algorithmic tools from optimization have been used to address problems in computational statistics, machine learning, and AI, starting over 200 years ago with least squares and continuing today with neural networks. We discuss the nature of current research at the interface of optimization and data science, which has both theoretical aspects (concerning the convergence properties of algorithms, the presence of "benign nonconvexity," the effectiveness of the optimization formulation in solving the underlying statistical problem, and other issues) and practical aspects (for example, the choice of algorithms and algorithmic parameters for matrix optimization problems and neural network training). Finally, we briefly survey some areas of ongoing research and open issues.

Stephen J. Wright holds the George B. Dantzig Professorship, the Sheldon Lubar Chair, and the Amar and Balinder Sohi Professorship of Computer Sciences at the University of Wisconsin-Madison. His research is in computational optimization and its applications to data science and many other areas of science and engineering. Prior to joining UW-Madison in 2001, Wright held positions at North Carolina State University (1986-1990) and Argonne National Laboratory (1990-2001). He has served as Chair of the Mathematical Optimization Society (2007-2010) and as a Trustee of SIAM for the maximum three terms (2005-2014). He is a Fellow of SIAM. In 2014, he won the W.R.G. Baker Award from IEEE for best paper in an IEEE archival publication during 2009-2011. He was awarded the Khachiyan Prize by the INFORMS Optimization Society in 2020 for lifetime achievements in optimization and received the NeurIPS Test of Time Award in 2020 for a paper presented at that conference in 2011. <br>Prof. Wright is the author / coauthor of widely used text and reference books in optimization including "Primal Dual Interior Point Methods" and "Numerical Optimization" and, most recently, "Optimization for Data Analysis." He has published widely on optimization theory, algorithms, software, and applications. <br> Prof. Wright served from 2014-2019 as Editor in Chief of the SIAM Journal on Optimization and previously served as Editor-in-Chief of Mathematical Programming Series B. He has also served as Associate Editor of Mathematical Programming Series A, SIAM Review, SIAM Journal on Scientific Computing, and several other journals and book series.