Abstract: Will quantum computing surpass classical methods in machine learning and optimization? In this talk, I will argue that answering this question requires understanding the boundaries of both quantum and classical computation, particularly in the current era of rapid progress in deep learning. On the quantum side, I will discuss theoretical advances in quantum neural networks and optimization of random quantum systems, highlighting both opportunities and limitations. For classical systems, I will present rigorous results on provable guarantees for neural networks and investigate how constraints like symmetry and locality can change networks’ ability to efficiently learn physics-inspired functions. Together, these insights aim to clarify the unique strengths and challenges of quantum and classical methods in tackling computational problems.
Bio: Bobak Kiani is a postdoc at Harvard University in the Applied Mathematics and Computer Science department in Melanie Weber’s group. Before this, he was a PhD student at MIT studying Electrical Engineering and Computer Science working with Seth Lloyd. His research areas are related to machine learning and quantum computation. In quantum computation, his work focuses on learning the limits and capabilities of algorithms especially those related to quantum learning and optimization. He has recently become more interested as well in studying average case complexity for quantum problems. On the classical side, he is interested in topics in machine learning tied to geometry and symmetry.
The Physics Frontiers Centers (PFC) program supports university-based centers and institutes where the collective efforts of a larger group of individuals can enable transformational advances in the most promising research areas. The program is designed to foster major breakthroughs at the intellectual frontiers of physics by providing needed resources such as combinations of talents, skills, disciplines, and/or specialized infrastructure, not usually available to individual investigators or small groups, in an environment in which the collective efforts of the larger group can be shown to be seminal to promoting significant progress in the science and the education of students. PFCs also include creative, substantive activities aimed at enhancing education, broadening participation of traditionally underrepresented groups, and outreach to the scientific community and general public.