PIRSA:18080000

Convex Programming and Machine Learning in Quantum Information: Complementary Methods for Discovery and Verification

Wittek, P. (2018). Convex Programming and Machine Learning in Quantum Information: Complementary Methods for Discovery and Verification. Perimeter Institute. https://pirsa.org/18080000

Wittek, Peter. Convex Programming and Machine Learning in Quantum Information: Complementary Methods for Discovery and Verification. Perimeter Institute, Aug. 07, 2018, https://pirsa.org/18080000 

          @misc{ pirsa_PIRSA:18080000,
            doi = {10.48660/18080000},
            url = {https://pirsa.org/18080000},
            author = {Wittek, Peter},
            keywords = {Quantum Foundations},
            language = {en},
            title = {Convex Programming and Machine Learning in Quantum Information: Complementary Methods for Discovery and Verification},
            publisher = {Perimeter Institute},
            year = {2018},
            month = {aug},
            note = {PIRSA:18080000 see, \url{https://pirsa.org}}
          }

Peter Wittek

DOI 10.48660/18080000
Collection
Talk Type Scientific Series
Subject

Abstract

Convex optimization, linear and semidefinite programming in particular, has been a standard tool in quantum information theory, giving certificates of local and quantum correlations, contextuality, and more. Increasingly, similar methods are making headways in quantum many-body physics, giving lower bounds -- and thus certificates -- on the ground state energy. The disadvantage of such methods is that they do not scale well to large system sizes, whether those systems are multiparty Bell scenarios or lattice models of numerous sites. Machine
learning is entering the field as the latest buzzword. While it provides a more scalable alternative to convex programming and enables forming new conjectures, the outcome of learning methods remains uncertified. In this talk, I introduce the most important paradigms in machine learning for quantum information theory, give an overview of some earlier work in the field, argue for the importance of certifiable predictions of learning algorithms, and present some of our preliminary results.