【CS Peer Talk #9】Quantum Algorithms for Machine Learning and Optimization
The theories of optimization and machine learning answer fundamental questions in computer science and lead to new algorithms for practical applications. While these topics have been extensively studied in the context of classical computing, their quantum counterparts are far from well-understood. In this talk, I will introduce my research that bridges the gap between the fields of quantum computing and machine learning.
On the one hand, I will briefly introduce some of my recent developments on quantum speedups for optimization and machine learning. To be more specific, I will introduce fast quantum algorithms for both machine learning problems with input data stored explicitly as matrices ranging from semidefinite programs (QIP 2019) to classification (ICML 2019), as well as general optimization problems with function evaluations (QIP 2019, QIP 2020). As a complement, I will also introduce limitations of quantum machine learning (STOC 2020, QIP 2020). On the other hand, I will briefly introduce applications of machine learning techniques to quantum computing, including a quantum version of generative adversarial networks (NeurIPS 2019).
Tongyang Li will join the Massachusetts Institute of Technology as a postdoctoral associate in August, 2020. He received Master and PhD degrees from the Department of Computer Science, University of Maryland in 2018 and 2020, respectively. He received B.E. from Institute for Interdisciplinary Information Sciences, Tsinghua University and B.S. from Department of Mathematical Sciences, Tsinghua University, both in 2015. He was a recipient of the IBM Ph.D. Fellowship, the NSF QISE-NET Triplet Award, and the Lanczos Fellowship. His research focuses on designing quantum algorithms for machine learning and optimization.