{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,25]],"date-time":"2025-12-25T04:43:28Z","timestamp":1766637808147,"version":"build-2065373602"},"reference-count":43,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T00:00:00Z","timestamp":1692748800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["SCHN 457\/17-1","EXC-2181\/1"],"award-info":[{"award-number":["SCHN 457\/17-1","EXC-2181\/1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["SCHN 457\/17-1","EXC-2181\/1"],"award-info":[{"award-number":["SCHN 457\/17-1","EXC-2181\/1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>This paper introduces assignment flows for density matrices as state spaces for representation and analysis of data associated with vertices of an underlying weighted graph. Determining an assignment flow by geometric integration of the defining dynamical system causes an interaction of the non-commuting states across the graph, and the assignment of a pure (rank-one) state to each vertex after convergence. Adopting the Riemannian\u2013Bogoliubov\u2013Kubo\u2013Mori metric from information geometry leads to closed-form local expressions that can be computed efficiently and implemented in a fine-grained parallel manner. Restriction to the submanifold of commuting density matrices recovers the assignment flows for categorical probability distributions, which merely assign labels from a finite set to each data point. As shown for these flows in our prior work, the novel class of quantum state assignment flows can also be characterized as Riemannian gradient flows with respect to a non-local, non-convex potential after proper reparameterization and under mild conditions on the underlying weight function. This weight function generates the parameters of the layers of a neural network corresponding to and generated by each step of the geometric integration scheme. Numerical results indicate and illustrate the potential of the novel approach for data representation and analysis, including the representation of correlations of data across the graph by entanglement and tensorization.<\/jats:p>","DOI":"10.3390\/e25091253","type":"journal-article","created":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T10:06:48Z","timestamp":1692871608000},"page":"1253","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Quantum State Assignment Flows"],"prefix":"10.3390","volume":"25","author":[{"given":"Jonathan","family":"Schwarz","sequence":"first","affiliation":[{"name":"Image and Pattern Analysis Group, Institute for Mathematics, Heidelberg University, 69117 Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonas","family":"Cassel","sequence":"additional","affiliation":[{"name":"Image and Pattern Analysis Group, Institute for Mathematics, Heidelberg University, 69117 Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3490-3350","authenticated-orcid":false,"given":"Bastian","family":"Boll","sequence":"additional","affiliation":[{"name":"Image and Pattern Analysis Group, Institute for Mathematics, Heidelberg University, 69117 Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1914-7099","authenticated-orcid":false,"given":"Martin","family":"G\u00e4rttner","sequence":"additional","affiliation":[{"name":"Physikalisches Institut, Kirchhoff Institute for Physics, Heidelberg University, 69117 Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Albers","sequence":"additional","affiliation":[{"name":"Research Station Geometry & Dynamics, Institute for Mathematics, Heidelberg University, 69117 Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph","family":"Schn\u00f6rr","sequence":"additional","affiliation":[{"name":"Image and Pattern Analysis Group, Institute for Mathematics, Heidelberg University, 69117 Heidelberg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,8,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Bak\u0131r, G., Hofmann, T., Sch\u00f6lkopf, B., Smolar, A.J., Taskar, B., and Vishwanathan, S.V.N. (2007). Predicting Structured Data, MIT Press.","DOI":"10.7551\/mitpress\/7443.001.0001"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s10851-016-0702-4","article-title":"Image Labeling by Assignment","volume":"58","author":"Petra","year":"2017","journal-title":"J. Math. Imaging Vis."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Grohs, P., Holler, M., and Weinmann, A. (2020). Variational Methods for Nonlinear Geometric Data and Applications, Springer.","DOI":"10.1007\/978-3-030-31351-7"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1007\/s41884-021-00060-8","article-title":"Assignment Flows for Data Labeling on Graphs: Convergence and Stability","volume":"5","author":"Zern","year":"2022","journal-title":"Inf. Geom."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1007\/s10851-020-00977-2","article-title":"Learning Adaptive Regularization for Image Labeling Using Geometric Assignment","volume":"63","author":"Savarino","year":"2021","journal-title":"J. Math. Imaging Vis."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"3088","DOI":"10.1007\/s11263-021-01520-5","article-title":"Assignment Flow For Order-Constrained OCT Segmentation","volume":"129","author":"Sitenko","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1090\/S0273-0979-03-00988-1","article-title":"Evolutionary Game Dynamics","volume":"40","author":"Hofbauer","year":"2003","journal-title":"Bull. Am. Math. Soc."},{"key":"ref_8","unstructured":"Sandholm, W.H. (2010). Population Games and Evolutionary Dynamics, MIT Press."},{"key":"ref_9","unstructured":"Amari, S.-I., and Nagaoka, H. (2000). Methods of Information Geometry, Oxford University Press."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"034004","DOI":"10.1088\/1361-6420\/ab2772","article-title":"Geometric Numerical Integration of the Assignment Flow","volume":"36","author":"Zeilmann","year":"2020","journal-title":"Inverse Probl."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1137\/22M1496141","article-title":"A Nonlocal Graph-PDE and Higher-Order Geometric Integration for Image Labeling","volume":"16","author":"Sitenko","year":"2023","journal-title":"SIAM J. Imaging Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"982","DOI":"10.1007\/s10851-019-00935-7","article-title":"Unsupervised Assignment Flow: Label Learning on Feature Manifolds by Spatially Regularized Geometric Assignment","volume":"62","author":"Zern","year":"2020","journal-title":"J. Math. Imaging Vis."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1137\/19M1298639","article-title":"Self-Assignment Flows for Unsupervised Data Labeling on Graphs","volume":"13","author":"Zisler","year":"2020","journal-title":"SIAM J. Imaging Sci."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Bengtsson, I., and Zyczkowski, K. (2017). Geometry of Quantum States: An Introduction to Quantum Entanglement, Cambridge University Press. [2nd ed.].","DOI":"10.1017\/9781139207010"},{"key":"ref_15","unstructured":"Petz, D. (2008). Quantum Information Theory and Quantum Statistics, Springer."},{"key":"ref_16","unstructured":"Calatroni, L., Donatelli, M., Morigi, S., Prato, M., and Santacesaria, M. Scale Space and Variational Methods in Computer Vision, Springer."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Amari, S.-I. (1985). Differential-Geometrical Methods in Statistics, Springer. [1990 ed.]. Lecture Notes in Statistics.","DOI":"10.1007\/978-1-4612-5056-2"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Gupta, S.S., Amari, S.I., Barndorff-Nielsen, O.E., Kass, R.E., Lauritzen, S.L., and Rao, C.R. (1987). Differential Geometry in Statistical Inference, Institute of Mathematical Statistics.","DOI":"10.1214\/lnms\/1215467060"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Brown, L.D. (1986). Fundamentals of Statistical Exponential Families, Institute of Mathematical Statistics.","DOI":"10.1214\/lnms\/1215466757"},{"key":"ref_20","unstructured":"\u010cencov, N.N. (1981). Statistical Decision Rules and Optimal Inference, American Mathematical Society."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Brazitikos, S., Giannopoulos, A., Valettas, P., and Vritsiou, B.-H. (2014). Geometry of Isotropic Convex Bodies, American Mathematical Society.","DOI":"10.1090\/surv\/196"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ay, N., Jost, J., L\u00ea, H.V., and Schwachh\u00f6fer, L. (2017). Information Geometry, Springer.","DOI":"10.1007\/978-3-319-56478-4"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Calin, O., and Udriste, C. (2014). Geometric Modeling in Probability and Statistics, Springer.","DOI":"10.1007\/978-3-319-07779-6"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"780","DOI":"10.1063\/1.530611","article-title":"Geometry of Canonical Correlation on the State Space of a Quantum System","volume":"35","author":"Petz","year":"1994","journal-title":"J. Math. Phys."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1090\/conm\/747\/15047","article-title":"A Short History of Frames and Quantum Designs","volume":"Volume 747","author":"Bodmann","year":"2020","journal-title":"Topological Phases of Matter and Quantum Computation"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1007\/BF00739578","article-title":"The Bogoliubov Inner Product in Quantum Statistics","volume":"27","author":"Petz","year":"1993","journal-title":"Lett. Math. Phys."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1142\/S0219025701000462","article-title":"On the Uniqueness of the Chentsov Metric in Quantum Information Geometry","volume":"4","author":"Grasselli","year":"2001","journal-title":"Infin. Dimens. Anal. Quantum Probab. Relat. Top."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1016\/j.laa.2022.12.009","article-title":"O(n)-invariant Riemannian Metrics on SPD Matrices","volume":"61","author":"Thanwerdas","year":"2023","journal-title":"Linear Algebra Appl."},{"key":"ref_29","unstructured":"Bhatia, R. (2006). Positive Definite Matrices, Princeton University Press."},{"key":"ref_30","first-page":"211","article-title":"A Riemannian Geometry of the Multivariate Normal Model","volume":"11","author":"Skovgaard","year":"1984","journal-title":"Scand. J. Stat."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Bridson, M.R., and H\u00e4flinger, A. (1999). Metric Spaces of Non-Positive Curvature, Springer.","DOI":"10.1007\/978-3-662-12494-9"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Jost, J. (2017). Riemannian Geometry and Geometric Analysis, Springer. [7th ed.].","DOI":"10.1007\/978-3-319-61860-9"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1137\/050637996","article-title":"Geometric Means in a Novel Vector Space Structure on Symmetric Positive-Definite Matrices","volume":"29","author":"Arsigny","year":"2007","journal-title":"SIAM J. Matrix Anal. Appl."},{"key":"ref_34","first-page":"1","article-title":"The Curvature of the Bogoliubov-Kubo-Mori Scalar Product on Matrices","volume":"3","author":"Michor","year":"2000","journal-title":"Infin. Dimens. Anal. Quantum Probab. Relat. Top."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Rockafellar, R. (1970). Convex Analysis, Princeton University Press.","DOI":"10.1515\/9781400873173"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1017\/S0956792520000273","article-title":"Continuous-Domain Assignment Flows","volume":"32","author":"Savarino","year":"2021","journal-title":"Eur. J. Appl. Math."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Absil, P.A., Mahony, R., and Sepulchre, R. (2008). Optimization Algorithms on Matrix Manifolds, Princeton University Press.","DOI":"10.1515\/9781400830244"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Higham, N.J. (2008). Functions of Matrices: Theory and Computation, Society for Industrial and Applied Mathematics (SIAM).","DOI":"10.1137\/1.9780898717778"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Savarino, F., Albers, P., and Schn\u00f6rr, C. (2021). On the Geometric Mechanics of Assignment Flows for Metric Data Labeling. arXiv, (to appear in: Information Geometry).","DOI":"10.1007\/978-3-030-75549-2_32"},{"key":"ref_40","unstructured":"Levine, Y., Yakira, D., Cohen, N., and Shashua, A. (May, January 30). Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design. Proceedings of the Sixth International Conference on Learning Representations ICLR, Vancouver, BC, Canada."},{"key":"ref_41","unstructured":"Chen, R.T.Q., Rubanova, Y., Bettencourt, J., and Duvenaud, D. (2018, January 3\u20138). Neural Ordinary Differential Equations. Advances in Neural Information Processing Systems 31, Proceedings of the 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, QC, Canada."},{"key":"ref_42","unstructured":"Horn, R.A., and Johnson, C.R. (2013). Matrix Analysis, Cambridge University Press. [2nd ed.]."},{"key":"ref_43","unstructured":"Kobayashi, S., and Nomizu, K. (1969). Foundations of Differential Geometry, John Wiley & Sons."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/9\/1253\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:41:04Z","timestamp":1760128864000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/9\/1253"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,23]]},"references-count":43,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2023,9]]}},"alternative-id":["e25091253"],"URL":"https:\/\/doi.org\/10.3390\/e25091253","relation":{},"ISSN":["1099-4300"],"issn-type":[{"type":"electronic","value":"1099-4300"}],"subject":[],"published":{"date-parts":[[2023,8,23]]}}}