PIRSA:21100052

Video URL

https://pirsa.org/21100052

On quantum linear algebra for machine learning

Tang, E. (2021). On quantum linear algebra for machine learning . Perimeter Institute for Theoretical Physics. https://pirsa.org/21100052

Tang, Ewin. On quantum linear algebra for machine learning . Perimeter Institute for Theoretical Physics, Oct. 27, 2021, https://pirsa.org/21100052 

          @misc{ scivideos_PIRSA:21100052,
            doi = {10.48660/21100052},
            url = {https://pirsa.org/21100052},
            author = {Tang, Ewin},
            keywords = {Quantum Matter},
            language = {en},
            title = {On quantum linear algebra for machine learning },
            publisher = {Perimeter Institute for Theoretical Physics},
            year = {2021},
            month = {oct},
            note = {PIRSA:21100052 see, \url{https://scivideos.org/index.php/pirsa/21100052}}
          }

Ewin Tang University of Washington

Talk numberPIRSA:21100052
DOI10.48660/21100052
Source RepositoryPIRSA
Collection
Talk Type Scientific Series
Subject

Abstract

We will discuss quantum singular value transformation (QSVT), a simple unifying framework for quantum linear algebra algorithms developed by Gilyén, Low, Su, and Wiebe. QSVT is often applied to try to achieve quantum speedups for machine learning problems. We will see the typical structure of such an application, the barriers to achieving super-polynomial quantum speedup, and the state of the literature that's attempting to bypass these barriers. Along the way, we'll also see an interesting connection between quantum linear algebra and classical sampling and sketching algorithms(explored in the form of "quantum-inspired" classical algorithms).