On quantum backpropagation, information reuse, and cheating measurement collapse

Authors: Amira Abbas, Robbie King, Hsin-Yuan Huang, William J. Huggins, Ramis Movassagh, Dar Gilboa, Jarrod McClean

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We show that achieving backpropagation scaling is impossible without access to multiple copies of a state. With this added ability, we introduce an algorithm with foundations in shadow tomography that matches backpropagation scaling in quantum resources while reducing classical auxiliary computational costs to open problems in shadow tomography.
Researcher Affiliation Collaboration Amira Abbas Google Quantum AI, Venice, California 90291, USA University of Kwa Zulu-Natal, South Africa Qu Soft, University of Amsterdam, Science Park 123, 1098 XG Amsterdam, The Netherlands Robbie King Department of Computing and Mathematical Sciences, Caltech, Pasadena, CA 91125, USA Hsin-Yuan Huang Department of Computing and Mathematical Sciences, Caltech, Pasadena, CA 91125, USA Institute for Quantum Information and Matter, Caltech, Pasadena, CA 91125, USA William J. Huggins Google Quantum AI, Venice, California 90291, USA Ramis Movassagh Google Quantum AI, Venice, California 90291, USA Dar Gilboa Google Quantum AI, Venice, California 90291, USA Jarrod R. Mc Clean Google Quantum AI, Venice, California 90291, USA jmcclean@google.com
Pseudocode Yes Algorithm 1 Online and gentle shadow tomography
Open Source Code No The paper does not provide any statement or link indicating the availability of open-source code for the described methodology.
Open Datasets No The paper is theoretical and does not describe empirical experiments that involve training with datasets. It discusses a "quantum data setting" as a theoretical model rather than an empirical dataset.
Dataset Splits No The paper is theoretical and does not perform empirical experiments requiring dataset splits for validation.
Hardware Specification No The paper is theoretical and does not describe specific hardware used for running experiments. It mentions general "quantum devices" and references assumptions about quantum operations from external work, but does not state its own hardware specifications.
Software Dependencies No The paper is theoretical and does not provide specific software dependencies with version numbers for reproducibility.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with specific hyperparameters, training configurations, or system-level settings.