Quantum-inspired tensor completion

Lead Research Organisation: University College London
Department Name: Physics and Astronomy


Matrix completion involves filling in missing entries of a matrix. We shall consider this in the online setting. That is, at each time step, we receive a matrix entry, predict its value and receive its true label. Clearly, it is impossible to give a meaningful learning guarantee if we do not impose any constraints on the matrix structure. Common constraints include low rankness, and we shall consider a related measure called the margin complexity. There already exists a quantum-inspired approach for the matrix case, which is based on regularising the loss function with the quantum relative entropy. We have extended this to various settings, with the inclusion of side information and noise. We will also attempt to perform tensor completion with a suitably adapted version of this algorithm.


10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/R512400/1 01/10/2017 31/03/2022
1930168 Studentship EP/R512400/1 25/09/2017 30/08/2022 Fai Yu Lisa Tse
EP/R513143/1 01/10/2018 30/09/2023
1930168 Studentship EP/R513143/1 25/09/2017 30/08/2022 Fai Yu Lisa Tse
Description We designed an algorithm for matrix completion with side information, with provable theoretical guarantees.
Exploitation Route This could have applications in, for example, building algorithms for recommender systems. The theoretical contribution could also be relevant to the academic community.
Sectors Digital/Communication/Information Technologies (including Software),Other

Description Cheltenham Festival: Quantum Workshop 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Public/other audiences
Results and Impact Together with other university students in the country, we hosted a quantum stall at Cheltenham Science festival, demonstrating some of the properties of quantum physics using VR.
Year(s) Of Engagement Activity 2019