Past Event: Babuška Forum

Learning Optimization Algorithms from Data

Zhangyang "Atlas" Wang, Assistant Professor, Electrical and Computer Engineering, UT Austin

Abstract

Learning and optimization are closely related: state-of-the-art learning problems hinge on the sophisticated design of optimizers. On the other hand, the optimization cannot be considered as independent from data, since data may implicitly contain important information that guides optimization, as seen in the recent waves of meta-learning or learning to optimize. This talk will discuss Learning to Optimize (L2O), a nascent area that bridges classical optimization with the latest data-driven learning, by augmenting classical model-based optimization with learning-based components. By adapting their behavior to the properties of the input distribution, the "augmented'' algorithms may reduce their complexities by magnitudes, and/or improve their accuracy, while still preserving favorable theoretical guarantees such as convergence. I will start by diving into a case study on exploiting deep learning to solve the convex LASSO problem, showing its linear convergence in addition to superior parameter efficiency. I will next demonstrate our recent results on ensuring the robustness of L2O, say how applicable the algorithm remains to be, if the testing problem instances deviate from the training problem distribution. Then, our discussions will be extended to applying L2O approaches to practical problems. The talk will be concluded by a few thoughts and reflections, as well as pointers to potential future directions.

 

Biography

Professor Zhangyang “Atlas” Wang is currently an Assistant Professor of Electrical and Computer Engineering at UT Austin, leading the VITA research group (https://vita-group.github.io/). He was an Assistant Professor of Computer Science and Engineering, at the Texas A&M University, from 2017 to 2020. He received his Ph.D. degree in ECE from UIUC in 2016, advised by Professor Thomas S. Huang; and his B.E. degree in EEIS from USTC in 2012. Prof. Wang is broadly interested in the fields of machine learning, computer vision, optimization, and their interdisciplinary applications. His latest interests focus on automated machine learning (AutoML), learning-based optimization, machine learning robustness, and efficient deep learning. His research is gratefully supported by NSF, DARPA, ARL/ARO, as well as a few more industry and university grants. He is an elected technical committee member of IEEE MLSP; an associate editor of IEEE TCSVT (in which capacity he received the 2020 IEEE TCSVT Best Associate Editor Award); and frequently serves as area chairs, guest editors, invited speakers, various panelist positions and reviewers. He has received many research awards and scholarships, including most recently an ARO Young Investigator award, an IBM Faculty Research Award, an Amazon Research Award (AWS AI), an Adobe Data Science Research Award, a Young Faculty Fellow of TAMU, and four research competition prizes from CVPR/ICCV/ECCV.