{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T18:34:39Z","timestamp":1767206079740,"version":"build-2238731810"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T00:00:00Z","timestamp":1747180800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Appl. Math. Stat."],"abstract":"<jats:p>In recent years, a learning method for classifiers using tensor networks (TNs) has attracted attention. When constructing a classification function for high-dimensional data using a basis function model, a huge number of basis functions and coefficients are generally required, but the TN model makes it possible to avoid the curse of dimensionality by representing the huge coefficients using TNs. However, there is a problem with TN learning, namely the gradient vanishing, and learning using the gradient method cannot be performed efficiently. In this study, we propose a novel optimization algorithm for learning TN classifiers by using alternating least square (ALS) algorithm. Unlike conventional gradient-based methods, which suffer from vanishing gradients and inefficient training, our proposed approach can effectively minimize squared loss and logistic loss. To make ALS applicable to logistic regression, we introduce an auxiliary function derived from P\u00f3lya-Gamma augmentation, allowing logistic loss to be minimized as a weighted squared loss. We apply the proposed method to the MNIST classification task and discuss the effectiveness of the proposed method.<\/jats:p>","DOI":"10.3389\/fams.2025.1593680","type":"journal-article","created":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T01:40:28Z","timestamp":1747186828000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Expectation-maximization alternating least squares for tensor network logistic regression"],"prefix":"10.3389","volume":"11","author":[{"given":"Naoya","family":"Yamauchi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hidekata","family":"Hontani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Yokota","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,5,14]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1561\/2200000059","article-title":"Tensor networks for dimensionality reduction and large-scale optimization: part 1 low-rank tensor decompositions","volume":"9","author":"Cichocki","year":"2016","journal-title":"Found Trends Mach Learn"},{"key":"B2","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1561\/9781680832778","article-title":"Tensor networks for dimensionality reduction and large-scale optimization: part 2 applications and future perspectives","volume":"9","author":"Cichocki","year":"2017","journal-title":"Found Trends Mach Learn"},{"key":"B3","article-title":"Learning tensor networks with tensor cross interpolation: new algorithms and libraries","author":"Fern\u00e1ndez","year":"2024","journal-title":"arXiv preprint arXiv:240702454"},{"key":"B4","article-title":"Very basics of tensors with graphical notations: unfolding, calculations, and decompositions","author":"Yokota","year":"2024","journal-title":"arXiv preprint arXiv:241116094"},{"key":"B5","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1137\/090752286","article-title":"Tensor-train decomposition","volume":"33","author":"Oseledets","year":"2011","journal-title":"SIAM J Sci Comput"},{"key":"B6","article-title":"Tensor ring decomposition","author":"Zhao","year":"2016","journal-title":"arXiv preprint arXiv:160605535"},{"key":"B7","article-title":"Supervised learning with tensor networks","volume-title":"Advances in Neural Information Processing Systems","author":"Stoudenmire","year":"2016"},{"key":"B8","doi-asserted-by":"publisher","first-page":"2654","DOI":"10.1109\/TSP.2022.3175608","article-title":"Low-rank characteristic tensor density estimation part I: foundations","volume":"70","author":"Amiridi","year":"2022","journal-title":"IEEE Trans Signal Proc"},{"key":"B9","doi-asserted-by":"publisher","first-page":"2669","DOI":"10.1109\/TSP.2022.3158422","article-title":"Low-rank characteristic tensor density estimation part II: compression and latent density estimation","volume":"70","author":"Amiridi","year":"2022","journal-title":"IEEE Trans Signal Proc"},{"key":"B10","doi-asserted-by":"publisher","first-page":"4","DOI":"10.4171\/mag\/101","article-title":"Tensor networks in machine learning","volume":"126","author":"Sengupta","year":"2022","journal-title":"Eur Mathem Soc Magaz"},{"key":"B11","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1109\/TMBMC.2023.3272158","article-title":"Control flow in active inference systems-part II: tensor networks as general models of control flow","volume":"9","author":"Fields","year":"2023","journal-title":"IEEE Trans Molec Biol Multi-Scale Commun"},{"key":"B12","article-title":"Position: tensor networks are a valuable asset for green AI","volume-title":"Proceedings of ICML","author":"Memmel","year":"2024"},{"key":"B13","article-title":"Two-dimensional linear discriminant analysis","author":"Ye","year":"2004","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1700","DOI":"10.1109\/TPAMI.2007.1096","article-title":"General tensor discriminant analysis and gabor features for gait recognition","volume":"29","author":"Tao","year":"2007","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B15","article-title":"Speeding-up convolutional neural networks using fine-tuned CP-decomposition","author":"Lebedev","year":"2014","journal-title":"arXiv preprint arXiv:14126553"},{"key":"B16","article-title":"Tensorizing neural networks","author":"Novikov","year":"2015","journal-title":"Proceedings of NeurlPS"},{"key":"B17","article-title":"LoRA: low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"Proceedings of ICLR"},{"key":"B18","volume-title":"Pattern Recognition and Machine Learning","author":"Bishop","year":"2006"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1080\/01621459.2013.829001","article-title":"Bayesian inference for logistic models using P\u00f3lya-Gamma latent variables","volume":"108","author":"Polson","year":"2013","journal-title":"J Am Stat Assoc"},{"key":"B20","article-title":"Expectation-maximization for logistic regression","author":"Scott","year":"2013","journal-title":"arXiv preprint arXiv:13060040"},{"key":"B21","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/BF02310791","article-title":"Analysis of individual differences in multidimensional scaling via an N-way generalization of \u201cEckart-Young\u201d decomposition","volume":"35","author":"Carroll","year":"1970","journal-title":"Psychometrika"},{"key":"B22","first-page":"1","article-title":"Foundations of the PARAFAC procedure: Models and conditions for an \u201cexplanatory\u201d multimodal factor analysis","volume":"16","author":"Harshman","year":"1970","journal-title":"UCLA Working Paper Phonet"},{"key":"B23","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/BF02293599","article-title":"Principal component analysis of three-mode data by means of alternating least squares algorithms","volume":"45","author":"Kroonenberg","year":"1980","journal-title":"Psychometrika"},{"key":"B24","doi-asserted-by":"publisher","first-page":"A683","DOI":"10.1137\/100818893","article-title":"The alternating linear scheme for tensor optimization in the tensor train format","volume":"34","author":"Holtz","year":"2012","journal-title":"SIAM Sci Comput"},{"key":"B25","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1137\/07070111X","article-title":"Tensor decompositions and applications","volume":"51","author":"Kolda","year":"2009","journal-title":"SIAM Rev"},{"key":"B26","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1109\/MSP.2013.2297439","article-title":"Tensor decompositions for signal processing applications: from two-way to multiway component analysis","volume":"32","author":"Cichocki","year":"2015","journal-title":"IEEE Signal Process Mag"},{"key":"B27","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/BF02294758","article-title":"Majorization as a tool for optimizing a class of matrix functions","volume":"55","author":"Kiers","year":"1990","journal-title":"Psychometrika"},{"key":"B28","doi-asserted-by":"publisher","first-page":"794","DOI":"10.1109\/TSP.2016.2601299","article-title":"Majorization-minimization algorithms in signal processing, communications, and machine learning","volume":"65","author":"Sun","year":"2016","journal-title":"IEEE Trans Signal Proc"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"Dempster","year":"1977","journal-title":"J R Stat Soc"},{"key":"B30","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.chemolab.2004.07.003","article-title":"PARAFAC and missing values","volume":"75","author":"Tomasi","year":"2005","journal-title":"Chemometr Intell Labor Syst"}],"updated-by":[{"DOI":"10.3389\/fams.2025.1629658","type":"corrigendum","label":"Corrigendum","source":"publisher","updated":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000}}],"container-title":["Frontiers in Applied Mathematics and Statistics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fams.2025.1593680\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T03:07:49Z","timestamp":1751339269000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fams.2025.1593680\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,14]]},"references-count":30,"alternative-id":["10.3389\/fams.2025.1593680"],"URL":"https:\/\/doi.org\/10.3389\/fams.2025.1593680","relation":{},"ISSN":["2297-4687"],"issn-type":[{"value":"2297-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,14]]},"article-number":"1593680"}}