{"day":"20","conference":{"name":"ISIT: International Symposium on Information Theory","start_date":"2025-06-22","location":"Ann Arbor, MI, United States","end_date":"2025-06-27"},"oa_version":"None","acknowledgement":"The research of A.K. and N.W. was supported by the Israel Science Foundation (ISF), grant no. 1782/22.","date_updated":"2025-11-24T08:53:34Z","quality_controlled":"1","publication_identifier":{"isbn":["9798331543990"],"issn":["2157-8095"]},"citation":{"apa":"El Latif Kadry, A., Zhang, Y., & Weinberger, N. (2025). Mean estimation in high-dimensional binary timeinhomogeneous Markov Gaussian mixture models. In 2025 IEEE International Symposium on Information Theory Proceedings. Ann Arbor, MI, United States: IEEE. https://doi.org/10.1109/ISIT63088.2025.11195426","mla":"El Latif Kadry, Abd, et al. “Mean Estimation in High-Dimensional Binary Timeinhomogeneous Markov Gaussian Mixture Models.” 2025 IEEE International Symposium on Information Theory Proceedings, IEEE, 2025, doi:10.1109/ISIT63088.2025.11195426.","short":"A. El Latif Kadry, Y. Zhang, N. Weinberger, in:, 2025 IEEE International Symposium on Information Theory Proceedings, IEEE, 2025.","chicago":"El Latif Kadry, Abd, Yihan Zhang, and Nir Weinberger. “Mean Estimation in High-Dimensional Binary Timeinhomogeneous Markov Gaussian Mixture Models.” In 2025 IEEE International Symposium on Information Theory Proceedings. IEEE, 2025. https://doi.org/10.1109/ISIT63088.2025.11195426.","ama":"El Latif Kadry A, Zhang Y, Weinberger N. Mean estimation in high-dimensional binary timeinhomogeneous Markov Gaussian mixture models. In: 2025 IEEE International Symposium on Information Theory Proceedings. IEEE; 2025. doi:10.1109/ISIT63088.2025.11195426","ieee":"A. El Latif Kadry, Y. Zhang, and N. Weinberger, “Mean estimation in high-dimensional binary timeinhomogeneous Markov Gaussian mixture models,” in 2025 IEEE International Symposium on Information Theory Proceedings, Ann Arbor, MI, United States, 2025.","ista":"El Latif Kadry A, Zhang Y, Weinberger N. 2025. Mean estimation in high-dimensional binary timeinhomogeneous Markov Gaussian mixture models. 2025 IEEE International Symposium on Information Theory Proceedings. ISIT: International Symposium on Information Theory."},"publication_status":"published","date_published":"2025-10-20T00:00:00Z","author":[{"first_name":"Abd","full_name":"El Latif Kadry, Abd","last_name":"El Latif Kadry"},{"first_name":"Yihan","orcid":"0000-0002-6465-6258","last_name":"Zhang","full_name":"Zhang, Yihan","id":"2ce5da42-b2ea-11eb-bba5-9f264e9d002c"},{"first_name":"Nir","last_name":"Weinberger","full_name":"Weinberger, Nir"}],"abstract":[{"lang":"eng","text":"We explore the problem of mean estimation for a high-dimensional binary symmetric Gaussian mixture model, where the label (sign) follows a time-inhomogeneous Markov chain. We propose a spectral estimator based on a partition of a subset of the samples to blocks. We develop a computationally efficient algorithm to find the optimal blocks, and derive minimax lower bounds on the estimation loss of any estimator, which establish the effectiveness of our proposed estimator. The resulting minimax rate illuminates the interplay between the sample size, dimension, signal strength, and the memory on the loss."}],"department":[{"_id":"MaMo"}],"title":"Mean estimation in high-dimensional binary timeinhomogeneous Markov Gaussian mixture models","month":"10","publication":"2025 IEEE International Symposium on Information Theory Proceedings","_id":"20667","doi":"10.1109/ISIT63088.2025.11195426","date_created":"2025-11-23T23:01:39Z","article_processing_charge":"No","OA_type":"closed access","year":"2025","scopus_import":"1","publisher":"IEEE","language":[{"iso":"eng"}],"status":"public","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","type":"conference"}