TY - JOUR

T1 - Operationally meaningful representations of physical systems in neural networks

AU - Poulsen Nautrup, Hendrik

AU - Metger, Tony

AU - Iten, Raban

AU - Jerbi, Sofiene

AU - Trenkwalder, Lea M.

AU - Wilming, Henrik

AU - Briegel, Hans J.

AU - Renner, Renato

N1 - Funding Information: H P N, S J, L M T and H J B acknowledge support from the Austrian Science Fund (FWF) through the DK-ALM: W1259-N27 and SFB BeyondC F7102. R I, H W and R R acknowledge support from from the Swiss National Science Foundation through SNSF Project No. 200020_165843 and 200021_188541. T M acknowledges support from ETH Zürich and the ETH Foundation through the Excellence Scholarship & Opportunity Programme, and from the IQIM, an NSF Physics Frontiers Center (NSF Grant PHY-1125565) with support of the Gordon and Betty Moore Foundation (GBMF-12500028). S J also acknowledges the Austrian Academy of Sciences as a recipient of the DOC Fellowship. H J B acknowledges support by the Ministerium für Wissenschaft, Forschung, und Kunst Baden Württemberg (AZ:33-7533.-30-10/41/1) and by the European Research Council (ERC) under Project No. 101055129. This work was supported by the Swiss National Supercomputing Centre (CSCS) under Project ID da04.

PY - 2022/12/16

Y1 - 2022/12/16

N2 - To make progress in science, we often build abstract representations of physical systems that meaningfully encode information about the systems. Such representations ignore redundant features and treat parameters such as velocity and position separately because they can be useful for making statements about different experimental settings. Here, we capture this notion by formally defining the concept of operationally meaningful representations. We present an autoencoder architecture with attention mechanism that can generate such representations and demonstrate it on examples involving both classical and quantum physics. For instance, our architecture finds a compact representation of an arbitrary two-qubit system that separates local parameters from parameters describing quantum correlations.

AB - To make progress in science, we often build abstract representations of physical systems that meaningfully encode information about the systems. Such representations ignore redundant features and treat parameters such as velocity and position separately because they can be useful for making statements about different experimental settings. Here, we capture this notion by formally defining the concept of operationally meaningful representations. We present an autoencoder architecture with attention mechanism that can generate such representations and demonstrate it on examples involving both classical and quantum physics. For instance, our architecture finds a compact representation of an arbitrary two-qubit system that separates local parameters from parameters describing quantum correlations.

KW - Bloch vector

KW - neural networks

KW - quantum physics

KW - reinforcement learning

KW - representation learning

UR - http://www.scopus.com/inward/record.url?scp=85145253673&partnerID=8YFLogxK

U2 - 10.1088/2632-2153/ac9ae8

DO - 10.1088/2632-2153/ac9ae8

M3 - Article

AN - SCOPUS:85145253673

VL - 3

JO - Machine Learning: Science and Technology

JF - Machine Learning: Science and Technology

IS - 4

M1 - 045025

ER -