Title: Optimization with Superquantile Constraints: A Fast Computational Approach

Speaker: Prof. Ying Cui

Summary:
We present an efficient and scalable second-order computational framework for solving large-scale optimization problems with superquantile constraints. Unlike empirical risk models, superquantile models have non-separable constraints that make typical first-order algorithms difficult to scale. We address the challenge by adopting a hybrid of the second-order semismooth Newton method and the augmented Lagrangian method, which takes advantage of the structured sparsity brought by the risk sensitive measures. The key to make the proposed computational framework scalable in terms of the number of training data is that the matrix-vector multiplication in solving the resulting Newton system can be computed in a reduced space due to the aforementioned sparsity. The computational cost per iteration for the Newton method is similar or even smaller than that of the first-order method. Our developed solver is expected to help improve the reliability and accuracy of statistical estimation and prediction, as well as control the risk of adverse events for safety-critical applications.

Biography:
Ying Cui is currently an assistant professor in the Department of Industrial Engineering and Operations Research at the University of California Berkeley. Prior to that appointment, she was an assistant professor at the University of Minnesota. She worked as postdoc research associate in the Daniel J. Epstein Department of Industrial and Systems Engineering at the University of Southern California working with Professor Jong-Shi Pang. Cui completed her PhD in Mathematics at the National University of Singapore. Her research focuses on the mathematical foundation of data science with emphasis on optimization techniques for operations research, machine learning and statistical estimations. She is particularly interested in leveraging nonsmoothness to design efficient algorithms for large scale nonlinear optimization problems. She is the co-author of the recently published monograph “Modern Nonconvex Nondifferenable Optimization’’.

MEETING ID: 873 1557 5255; PASSWORD: 778635

WED 14 AUGUST 2024 14:00-15:00 (AEST, Melbourne Time)