Haihao (Sean) Lu’s research interests are in extending the computational and mathematical boundaries of methods for solving the large-scale optimization problems that arise in data science, machine learning, and operations research. In particular, he is interested in (i) theory of convex and non-convex optimization motivated by statistical/machine learning problems; (ii) data-driven decision making with applications in advertisement allocation and machine scheduling; (iii) huge-scaling linear programming solving in the distributed setting (with applications at Google). His work has been published in journals including Mathematical Programming and SIAM Journal on Optimization.
Lu obtained his Ph.D in Operations Research and Applied Mathematics at MIT in 2019, and his B.S. in Mathematics at Shanghai Jiao Tong University in 2014. Prior to joining Booth, he was a visiting researcher at Google research large-scale optimization team, where he primarily worked on designing and implementing a huge-scale linear programming solver.
The Landscape of Proximal Point Method for Nonconvex-Nonconcave Minimax Optimization, Benjamin Grimmer, Haihao Lu, Pratik Worah and Vahab Mirrokni.
An O(s^r)-Resolution ODE Framework for Discrete-Time Optimization Algorithms and Applications to Convex-Concave Saddle-Point Problems, Haihao Lu.
The Best of Many Worlds: Dual Mirror Descent for Online Allocation Problems, with Santiago Balseiro and Vahab Mirrokni.
Relatively-Smooth Convex Optimization by First-Order Methods, and Applications, Haihao Lu, Robert M. Freund and Yurii Nesterov