{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:37:15Z","timestamp":1759883835607,"version":"build-2065373602"},"reference-count":84,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Academia Sinica"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s10994-025-06872-4","type":"journal-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T18:39:22Z","timestamp":1758047962000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["R\u00e9nyi divergence in hidden Markov models"],"prefix":"10.1007","volume":"114","author":[{"given":"Cheng-Der","family":"Fuh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Su-Chi","family":"Fuh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan-Chen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuan-Ju","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"issue":"1","key":"6872_CR1","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1109\/18.481781","volume":"42","author":"E Arikan","year":"1996","unstructured":"Arikan, E. (1996). An inequality on guessing and its application to sequential decoding. IEEE Transactions on Information Theory, 42(1), 99\u2013105.","journal-title":"IEEE Transactions on Information Theory"},{"key":"6872_CR2","first-page":"1","volume":"21","author":"AR Asadi","year":"2020","unstructured":"Asadi, A. R., & Abbe, E. (2020). Chaining meets chain rule: Multilevel entropic regularization and training of neural networks. The Journal of Machine Learning Research, 21, 1\u201332.","journal-title":"The Journal of Machine Learning Research"},{"key":"6872_CR3","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1090\/S0002-9947-1978-0511425-0","volume":"245","author":"KB Athreya","year":"1978","unstructured":"Athreya, K. B., & Ney, P. (1978). A new approach to the limit theory of recurrent Markov chains. Transactions of the American Mathematical Society, 245, 493\u2013501.","journal-title":"Transactions of the American Mathematical Society"},{"issue":"5","key":"6872_CR4","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1214\/aop\/1176995429","volume":"6","author":"KB Athreya","year":"1978","unstructured":"Athreya, K. B., McDonald, D., & Ney, P. E. (1978). Limit theorems for semi-Markov processes and renewal theory for Markov chains. The Annals of Probability, 6(5), 788\u2013797.","journal-title":"The Annals of Probability"},{"key":"6872_CR5","doi-asserted-by":"crossref","unstructured":"Atkinson, K.E. (1997). The numerical solution of integral equations of the second kind. Cambridge Monographs on Applied and Computational Mathematics.","DOI":"10.1017\/CBO9780511626340"},{"issue":"3","key":"6872_CR6","doi-asserted-by":"crossref","first-page":"324","DOI":"10.1109\/TIT.1978.1055890","volume":"24","author":"MB Bassat","year":"1978","unstructured":"Bassat, M. B., & Raviv, J. (1978). R\u00e9nyi\u2019s entropy and the probability of error. IEEE Transactions on Information Theory, 24(3), 324\u2013330.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"5","key":"6872_CR7","first-page":"143","volume":"3","author":"DH Blackwell","year":"1959","unstructured":"Blackwell, D. H. (1959). The entropy of functions of finite-state Markov chains. Matematika, 3(5), 143\u2013150.","journal-title":"Matematika"},{"issue":"4","key":"6872_CR8","doi-asserted-by":"crossref","first-page":"1275","DOI":"10.1109\/TAES.2009.5310298","volume":"45","author":"WR Blanding","year":"2009","unstructured":"Blanding, W. R., Willett, P. K., Bar-Shalom, Y., & Coraluppi, S. (2009). Multisensor track management for targets with fluctuating SNR. IEEE Transactions on Aerospace and Electronic Systems, 45(4), 1275\u20131292.","journal-title":"IEEE Transactions on Aerospace and Electronic Systems"},{"issue":"5","key":"6872_CR9","doi-asserted-by":"crossref","first-page":"1242","DOI":"10.1109\/18.21251","volume":"34","author":"AC Blumer","year":"1988","unstructured":"Blumer, A. C., & McEliece, R. J. (1988). The R\u00e9nyi redundancy of generalized Huffman codes. IEEE Transactions on Information Theory, 34(5), 1242\u20131249.","journal-title":"IEEE Transactions on Information Theory"},{"key":"6872_CR10","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/BF00322018","volume":"78","author":"P Bougerol","year":"1988","unstructured":"Bougerol, P. (1988). Th\u00e9or\u00e8mes limite pour les syst\u00e8mes lin\u00e9aires \u00e0 coefficients Markoviens. Probability Theory and Related Fields, 78, 193\u2013221.","journal-title":"Probability Theory and Related Fields"},{"key":"6872_CR11","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4684-9172-2","volume-title":"Products of random matrices with applications to Schr\u00f6dinger operators","author":"P Bougerol","year":"1985","unstructured":"Bougerol, P., & Lacroix, J. (1985). Products of random matrices with applications to Schr\u00f6dinger operators. Birkh\u00e4user."},{"issue":"1\u20132","key":"6872_CR12","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/0304-4076(92)90067-2","volume":"52","author":"P Bougerol","year":"1992","unstructured":"Bougerol, P., & Picard, N. (1992). Stationarity of GARCH processes and some nonnegative time series. Journal of Econometrics, 52(1\u20132), 115\u2013127.","journal-title":"Journal of Econometrics"},{"key":"6872_CR13","unstructured":"Buys, J., Bisk, Y., & Choi, Y. (2018). Bridging HMMs and RNNs through architectural transformations. In Proceedings of the 32nd conference on neural information processing systems, workshop IRASL."},{"issue":"4","key":"6872_CR14","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1016\/S0019-9958(65)90332-3","volume":"8","author":"LL Campbell","year":"1965","unstructured":"Campbell, L. L. (1965). A coding theorem and R\u00e9nyi\u2019s entropy. Information and Control, 8(4), 423\u2013429.","journal-title":"Information and Control"},{"key":"6872_CR15","doi-asserted-by":"crossref","DOI":"10.1007\/0-387-28982-8","volume-title":"Inference in hidden Markov models","author":"O Capp\u00e9","year":"2005","unstructured":"Capp\u00e9, O., Moulines, E., & Ryd\u00e9n. (2005). Inference in hidden Markov models. Springer-Verlag."},{"issue":"2","key":"6872_CR16","first-page":"395","volume":"13","author":"HP Chan","year":"2003","unstructured":"Chan, H. P., & Lai, T. L. (2003). Saddlepoint approximations and nonlinear boundary crossing probabilities of Markov random walks. The Annals of Applied Probability, 13(2), 395\u2013429.","journal-title":"The Annals of Applied Probability"},{"issue":"1","key":"6872_CR17","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1109\/18.904531","volume":"47","author":"PN Chen","year":"2001","unstructured":"Chen, P. N., & Alajaji, F. (2001). Csisz\u00e1r\u2019s cutoff rates for arbitrary discrete sources. IEEE Transactions on Information Theory, 47(1), 330\u2013338.","journal-title":"IEEE Transactions on Information Theory"},{"key":"6872_CR18","doi-asserted-by":"crossref","unstructured":"Cho, K., Van\u00a0Merri\u00ebnboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoder\u2013decoder for statistical machine translation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP) (pp. 1724\u20131734).","DOI":"10.3115\/v1\/D14-1179"},{"key":"6872_CR19","unstructured":"Chung, J., Kastner, K., Dinh, L., Goel, K., Courville, A.C., & Bengio, Y. (2015) A recurrent latent variable model for sequential data. In Advances in neural information processing systems."},{"issue":"1","key":"6872_CR20","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1007\/BF02458837","volume":"51","author":"GA Churchill","year":"1989","unstructured":"Churchill, G. A. (1989). Stochastic models for heterogeneous DNA sequences. Bulletin of Mathematical Biology, 51(1), 79\u201394.","journal-title":"Bulletin of Mathematical Biology"},{"issue":"1","key":"6872_CR21","doi-asserted-by":"crossref","first-page":"382","DOI":"10.1214\/aoap\/1015961169","volume":"12","author":"JF Collamore","year":"2002","unstructured":"Collamore, J. F. (2002). Importance sampling techniques for the multidimensional ruin problem for general Markov additive sequences of random vectors. The Annals of Applied Probability, 12(1), 382\u2013421.","journal-title":"The Annals of Applied Probability"},{"key":"6872_CR22","first-page":"697","volume":"15","author":"E Coviello","year":"2014","unstructured":"Coviello, E., Chan, A. B., & Lanckriet, G. R. G. (2014). Clustering hidden Markov models with variational HEM. The Journal of Machine Learning Research, 15, 697\u2013747.","journal-title":"The Journal of Machine Learning Research"},{"issue":"1","key":"6872_CR23","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/18.370121","volume":"41","author":"I Csiszar","year":"1995","unstructured":"Csiszar, I. (1995). Generalized cutoff rates and R\u00e9nyi\u2019s information measures. IEEE Transactions on Information Theory, 41(1), 26\u201334.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"5","key":"6872_CR24","doi-asserted-by":"crossref","first-page":"2254","DOI":"10.1214\/009053604000000021","volume":"32","author":"R Douc","year":"2004","unstructured":"Douc, R., Moulines, \u00c9., & Ryd\u00e9n, T. (2004). Asymptotic properties of the maximum likelihood estimator in autoregressive models with Markov regime. The Annals of Statistics, 32(5), 2254\u20132304.","journal-title":"The Annals of Statistics"},{"issue":"6","key":"6872_CR25","doi-asserted-by":"crossref","first-page":"1518","DOI":"10.1109\/TIT.2002.1003838","volume":"48","author":"Y Ephraim","year":"2002","unstructured":"Ephraim, Y., & Merhav, N. (2002). Hidden Markov processes. IEEE Transactions on Information Theory, 48(6), 1518\u20131569.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"1","key":"6872_CR26","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1109\/18.904523","volume":"47","author":"U Erez","year":"2001","unstructured":"Erez, U., & Zamir, R. (2001). Error exponents of modulo-additive noise channels with side information at the transmitter. IEEE Transactions on Information Theory, 47(1), 210\u2013218.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"7","key":"6872_CR27","doi-asserted-by":"crossref","first-page":"3797","DOI":"10.1109\/TIT.2014.2320500","volume":"60","author":"T van Erven","year":"2014","unstructured":"van Erven, T., & Harremo\u00ebs, P. (2014). R\u00e9nyi divergence and Kullback\u2013Leibler divergence. IEEE Transactions on Information Theory, 60(7), 3797\u20133820.","journal-title":"IEEE Transactions on Information Theory"},{"key":"6872_CR28","first-page":"942","volume":"31","author":"CD Fuh","year":"2003","unstructured":"Fuh, C. D. (2003). SPRT and CUSUM in hidden Markov models. Annals of Statistics, 31, 942\u2013977.","journal-title":"Annals of Statistics"},{"issue":"1","key":"6872_CR29","first-page":"127","volume":"14","author":"CD Fuh","year":"2004","unstructured":"Fuh, C. D. (2004). On Bahadur efficiency of the maximum likelihood estimator in hidden Markov models. Statistica Sinica, 14(1), 127\u2013144.","journal-title":"Statistica Sinica"},{"key":"6872_CR30","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1016\/j.spa.2021.04.009","volume":"138","author":"CD Fuh","year":"2021","unstructured":"Fuh, C. D. (2021). Asymptotic behavior for Markovian iterated function systems. Stochastic Processes and their Applications, 138, 186\u2013211.","journal-title":"Stochastic Processes and their Applications"},{"issue":"1","key":"6872_CR31","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1109\/TIT.2020.3029096","volume":"67","author":"CD Fuh","year":"2021","unstructured":"Fuh, C. D. (2021). Asymptotically optimal change point detection for composite hypothesis in state space models. IEEE Transactions on Information Theory, 67(1), 485\u2013505.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"18","key":"6872_CR32","doi-asserted-by":"crossref","first-page":"4866","DOI":"10.1109\/TSP.2015.2447506","volume":"63","author":"CD Fuh","year":"2015","unstructured":"Fuh, C. D., & Mei, Y. (2015). Quickest change detection and Kullback\u2013Leibler divergence for two-state hidden Markov models. IEEE Transactions on Signal Processing, 63(18), 4866\u20134878.","journal-title":"IEEE Transactions on Signal Processing"},{"issue":"1","key":"6872_CR33","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1109\/TIT.2018.2843379","volume":"65","author":"CD Fuh","year":"2019","unstructured":"Fuh, C. D., & Tartakovsky, A. G. (2019). Asymptotic Bayesian theory of quickest change detection for hidden Markov models. IEEE Transactions on Information Theory, 65(1), 511\u2013529.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"8","key":"6872_CR34","doi-asserted-by":"crossref","first-page":"5888","DOI":"10.1109\/TIT.2024.3392983","volume":"70","author":"CD Fuh","year":"2024","unstructured":"Fuh, C. D., Kao, C. L., & Pang, T. (2024). Kullback-Leibler divergence and Akaike information criterion in general hidden Markov models. IEEE Transactions on Information Theory, 70(8), 5888\u20135909.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"4","key":"6872_CR35","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1162\/089976600300015619","volume":"12","author":"Z Ghahramani","year":"2000","unstructured":"Ghahramani, Z., & Hinton, G. E. (2000). Variational learning for switching state-space models. Neural Computation, 12(4), 831\u2013864.","journal-title":"Neural Computation"},{"key":"6872_CR36","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1023\/A:1007425814087","volume":"29","author":"Z Ghahramani","year":"1997","unstructured":"Ghahramani, Z., & Jordan, M. I. (1997). Factorial hidden Markov models. Machine Learning, 29, 245\u2013273.","journal-title":"Machine Learning"},{"key":"6872_CR37","doi-asserted-by":"crossref","unstructured":"Girardin, V., & Regnault, P. (2020). R\u00e9nyi divergence rates of ergodic Markov chains: Existence, explicit expressions and properties. In 2020 IEEE international symposium on information theory (ISIT) (pp. 2275\u20132279).","DOI":"10.1109\/ISIT44484.2020.9174127"},{"key":"6872_CR38","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press."},{"issue":"2","key":"6872_CR39","doi-asserted-by":"crossref","first-page":"357","DOI":"10.2307\/1912559","volume":"57","author":"JD Hamilton","year":"1989","unstructured":"Hamilton, J. D. (1989). A new approach to the economic analysis of nonstationary time series and the business cycle. Econometrica, 57(2), 357\u2013384.","journal-title":"Econometrica"},{"key":"6872_CR40","doi-asserted-by":"crossref","unstructured":"Han, G., & Marcus, B. (2006a). Analyticity of entropy rate in families of hidden Markov chains (II). In Proceedings of the 2006 IEEE International Symposium on Information Theory (pp. 103\u2013107).","DOI":"10.1109\/ISIT.2006.261683"},{"issue":"12","key":"6872_CR41","doi-asserted-by":"crossref","first-page":"5251","DOI":"10.1109\/TIT.2006.885481","volume":"52","author":"G Han","year":"2006","unstructured":"Han, G., & Marcus, B. (2006). Analyticity of entropy rate of hidden Markov chains. IEEE Transactions on Information Theory, 52(12), 5251\u20135266.","journal-title":"IEEE Transactions on Information Theory"},{"key":"6872_CR42","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/S0377-0427(01)00390-9","volume":"139","author":"G Han","year":"2002","unstructured":"Han, G., & Wang, R. (2002). Richardson extrapolation of iterated discrete Galerkin solution for two-dimensional Fredholm integral equations. Journal of Computational and Applied Mathematics, 139, 49\u201363.","journal-title":"Journal of Computational and Applied Mathematics"},{"issue":"1","key":"6872_CR43","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1017\/S0143385709000030","volume":"30","author":"N Haydn","year":"2010","unstructured":"Haydn, N., & Vaienti, S. (2010). The R\u00e9nyi entropy function and the large deviation of short return times. Ergodic Theorem and Dynamical Systems, 30(1), 159\u2013179.","journal-title":"Ergodic Theorem and Dynamical Systems"},{"issue":"4","key":"6872_CR44","doi-asserted-by":"crossref","first-page":"1545","DOI":"10.1214\/aop\/1023481103","volume":"25","author":"H Hennion","year":"1997","unstructured":"Hennion, H. (1997). Limit theorems for products of positive random matrices. The Annals of Probability, 25(4), 1545\u20131587.","journal-title":"The Annals of Probability"},{"issue":"8","key":"6872_CR45","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735\u20131780.","journal-title":"Neural Computation"},{"issue":"10","key":"6872_CR46","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1109\/34.541414","volume":"18","author":"J Hu","year":"1996","unstructured":"Hu, J., Brown, M. K., & Turin, W. (1996). HMM based online handwriting recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(10), 1039\u20131045.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2\u20133","key":"6872_CR47","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/j.tcs.2008.01.012","volume":"395","author":"P Jacquet","year":"2008","unstructured":"Jacquet, P., Seroussi, G., & Szpankowski, W. (2008). On the entropy of a hidden Markov process. Theoretical Computer Science, 395(2\u20133), 203\u2013219.","journal-title":"Theoretical Computer Science"},{"issue":"3","key":"6872_CR48","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1109\/TIT.1968.1054147","volume":"14","author":"F Jelinek","year":"1968","unstructured":"Jelinek, F. (1968). Buffer overflow in variable length coding of fixed rate sources. IEEE Transactions on Information Theory, 14(3), 490\u2013501.","journal-title":"IEEE Transactions on Information Theory"},{"key":"6872_CR49","doi-asserted-by":"crossref","unstructured":"Jenssen, R., Hild, K.E., Erdogmus, D., Principe, J.C., & Eltoft, T. (2003). Clustering using Renyi\u2019s entropy. In Proceedings of the international joint conference on neural networks (pp. 523\u2013528).","DOI":"10.1109\/IJCNN.2003.1223401"},{"issue":"1","key":"6872_CR50","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/0304-4149(96)00060-9","volume":"63","author":"R Khasminskii","year":"1996","unstructured":"Khasminskii, R., & Zeitouni, O. (1996). Asymptotic filtering for finite state Markov chains. Stochastic Processes and Their Applications, 63(1), 1\u201310.","journal-title":"Stochastic Processes and Their Applications"},{"key":"6872_CR51","doi-asserted-by":"crossref","first-page":"982","DOI":"10.1214\/aoms\/1177705671","volume":"31","author":"LH Koopmans","year":"1960","unstructured":"Koopmans, L. H. (1960). Asymptotic rate of discrimination for Markov processes. The Annals of Mathematical Statistics, 31, 982\u2013994.","journal-title":"The Annals of Mathematical Statistics"},{"issue":"3","key":"6872_CR52","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/0031-3203(89)90076-9","volume":"22","author":"A Kunda","year":"1989","unstructured":"Kunda, A., He, Y., & Bahl, P. (1989). Recognition of handwritten word: First and second order hidden Markov model based approach. Pattern Recognition, 22(3), 283\u2013297.","journal-title":"Pattern Recognition"},{"key":"6872_CR53","first-page":"1","volume":"18","author":"L Lin","year":"2017","unstructured":"Lin, L., & Li, J. (2017). Clustering with hidden Markov model on variational blocks. The Journal of Machine Learning Research, 18, 1\u201349.","journal-title":"The Journal of Machine Learning Research"},{"key":"6872_CR54","unstructured":"Metelli, A.M., Papini, M., Faccio, F., & Restelli, M. (2018). Policy optimization via importance sampling. In Advances in neural information processing systems, 31."},{"key":"6872_CR55","first-page":"1","volume":"21","author":"AM Metelli","year":"2020","unstructured":"Metelli, A. M., Papini, M., Montali, N., & Restelli, M. (2020). Importance sampling techniques for policy optimization. The Journal of Machine Learning Research, 21, 1\u201375.","journal-title":"The Journal of Machine Learning Research"},{"key":"6872_CR56","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511626630","volume-title":"Markov chains and stochastic stability","author":"SP Meyn","year":"2009","unstructured":"Meyn, S. P., & Tweedie, R. L. (2009). Markov chains and stochastic stability. Cambridge University Press."},{"key":"6872_CR57","unstructured":"Miller, J., & Hardt, M. (2019). Stable recurrent models. In Proceedings of international conference on learning representations."},{"issue":"2","key":"6872_CR58","first-page":"147","volume":"3","author":"T Nemetz","year":"1974","unstructured":"Nemetz, T. (1974). On the $$\\alpha $$-divergence rate for Markov-dependent hypotheses. Problems of Control and Information Theory, 3(2), 147\u2013155.","journal-title":"Problems of Control and Information Theory"},{"issue":"2","key":"6872_CR59","first-page":"561","volume":"15","author":"P Ney","year":"1987","unstructured":"Ney, P., & Nummelin, E. (1987). Markov additive processes I. Eigenvalue properties and limit theorems. The Annals of Probability, 15(2), 561\u2013592.","journal-title":"The Annals of Probability"},{"issue":"2","key":"6872_CR60","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1016\/0304-4149(86)90001-3","volume":"22","author":"S Niemi","year":"1986","unstructured":"Niemi, S., & Nummelin, E. (1986). On non-singular renewal kernels with an application to a semigroup of transition kernels. Stochastic Processes and Their Applications, 22(2), 177\u2013202.","journal-title":"Stochastic Processes and Their Applications"},{"key":"6872_CR61","doi-asserted-by":"crossref","unstructured":"Ordentlich, E., & Weissman, T. (2004). New bounds on the entropy rate of hidden Markov processes. In Proceedings of information theory workshop (pp. 117\u2013122).","DOI":"10.1109\/ITW.2004.1405285"},{"issue":"1","key":"6872_CR62","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/TIT.2005.860432","volume":"52","author":"E Ordentlich","year":"2005","unstructured":"Ordentlich, E., & Weissman, T. (2005). On the optimality of symbol by symbol filtering and denoising. IEEE Transactions on Information Theory, 52(1), 19\u201340.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"2","key":"6872_CR63","doi-asserted-by":"crossref","first-page":"2018","DOI":"10.1103\/PhysRevE.62.2018","volume":"62","author":"A Ostruszka","year":"2000","unstructured":"Ostruszka, A., Pako\u0144ski, P., S\u0142omczy\u0144ski, W., & \u017byczkowski, K. (2000). Dynamical entropy for systems with stochastic perturbation. Physical Review E, 62(2), 2018.","journal-title":"Physical Review E"},{"key":"6872_CR64","unstructured":"Papini, M., Metelli, A.M., Lupo, L., & Restelli, M. (2019). Optimistic policy optimization via multiple importance sampling. In Proceedings of international conference on machine learning (pp. 4989\u20134999)."},{"key":"6872_CR65","unstructured":"Press, W.H., Teukolsky, S.A., Vetterling, W.T., & Flannery, B.P. (2007). Section 19.1. Fredholm equations of the second kind. In Numerical recipes: The art of scientific computing (3rd ed.). Cambridge University Press."},{"key":"6872_CR66","first-page":"253","volume":"33","author":"L Pronzato","year":"1997","unstructured":"Pronzato, L., Wynn, H. P., & Zhigljavsky, A. A. (1997). Using R\u00e9nyi entropies to measure uncertainty in search problems. Lectures in Applied Mathematics, 33, 253\u2013268.","journal-title":"Lectures in Applied Mathematics"},{"issue":"2","key":"6872_CR67","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"LR Rabiner","year":"1989","unstructured":"Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257\u2013286.","journal-title":"Proceedings of the IEEE"},{"key":"6872_CR68","volume-title":"Fundamentals of speech recognition","author":"LR Rabiner","year":"1993","unstructured":"Rabiner, L. R., & Juang, B. H. (1993). Fundamentals of speech recognition. Prentice Hall."},{"issue":"4","key":"6872_CR69","doi-asserted-by":"crossref","first-page":"1553","DOI":"10.1109\/18.923736","volume":"47","author":"Z Rached","year":"2001","unstructured":"Rached, Z., Alajaji, F., & Campbell, L. L. (2001). R\u00e9nyi\u2019s divergence and entropy rates for finite alphabet Markov sources. IEEE Transactions on Information Theory, 47(4), 1553\u20131561.","journal-title":"IEEE Transactions on Information Theory"},{"issue":"4","key":"6872_CR70","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.1214\/13-AOAS682","volume":"7","author":"V Raghavan","year":"2013","unstructured":"Raghavan, V., Galstyan, A., & Tartakovsky, A. G. (2013). Hidden Markov models for the activity profile of terrorist groups. The Annals of Applied Statistics, 7(4), 2402\u20132430.","journal-title":"The Annals of Applied Statistics"},{"issue":"1","key":"6872_CR71","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1109\/TCSS.2014.2307453","volume":"1","author":"V Raghavan","year":"2014","unstructured":"Raghavan, V., Steeg, G., Galstyan, A., & Tartakovsky, A. G. (2014). Modeling temporal activity patterns in dynamic social networks. IEEE Transactions on Computational Social Systems, 1(1), 89\u2013107.","journal-title":"IEEE Transactions on Computational Social Systems"},{"key":"6872_CR72","unstructured":"R\u00e9nyi, A. (1961). On measures of entropy and information. In Proceedings of the Fourth Berkeley symposium on mathematical statistics and probability, volume 1: contributions to the theory of statistics (pp. 547\u2013562), University of California Press ."},{"key":"6872_CR73","first-page":"1","volume":"23","author":"L Rimella","year":"2022","unstructured":"Rimella, L., & Whiteley, N. (2022). Exploiting locality in high-dimensional factorial hidden Markov models. The Journal of Machine Learning Research, 23, 1\u201334.","journal-title":"The Journal of Machine Learning Research"},{"key":"6872_CR74","unstructured":"Salakhutdinov, R., & Hinton, G.E. (2009). Deep Boltzmann machines. In Proc 12th Int Conf Artif Intell Statist (AISTATS) (pp. 448\u2013455)."},{"issue":"1","key":"6872_CR75","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1063\/1.166492","volume":"10","author":"W S\u0142omczy\u0144ski","year":"2000","unstructured":"S\u0142omczy\u0144ski, W., Kwapie\u0144, J., & \u017byczkowski, K. (2000). Entropy computing via integration over fractal measures. Chaos: An Interdisciplinary Journal of Nonlinear Science, 10(1), 180\u2013188.","journal-title":"Chaos: An Interdisciplinary Journal of Nonlinear Science"},{"key":"6872_CR76","unstructured":"Sutskever, I., Hinton, G.E., & Taylor, G. (2008). The recurrent temporal restricted Boltzmann machine. In Proc NIPS (pp. 1601\u20131608)."},{"issue":"1","key":"6872_CR77","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1007\/s11071-010-9724-4","volume":"62","author":"JA Tenreiro Machado","year":"2010","unstructured":"Tenreiro Machado, J. A. (2010). Entropy analysis of integer and fractional dynamical systems. Nonlinear Dynamics, 62(1), 371\u2013378.","journal-title":"Nonlinear Dynamics"},{"key":"6872_CR78","doi-asserted-by":"crossref","unstructured":"Tu\u011fa\u00e7, S., & Efe, M. (2010). Hidden Markov model based target detection. In Proceedings of the 2010 13th international conference on information fusion (pp. 1\u20137).","DOI":"10.1109\/ICIF.2010.5711878"},{"key":"6872_CR79","first-page":"179","volume":"10","author":"S Vasuhi","year":"2014","unstructured":"Vasuhi, S., & Vaidehi, V. (2014). Target detection and tracking for video surveillance. WSEAS Transactions on Signal Processing, 10, 179\u2013188.","journal-title":"WSEAS Transactions on Signal Processing"},{"key":"6872_CR80","doi-asserted-by":"crossref","unstructured":"Wu, C., Xu, E.L., & Han, G. (2017). R\u00e9nyi entropy rate of hidden Markov processes. In Proceedings of the 2017 IEEE international symposium on information theory (ISIT) (pp. 2970\u20132974).","DOI":"10.1109\/ISIT.2017.8007074"},{"issue":"1","key":"6872_CR81","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIT.2023.3318265","volume":"70","author":"C Wu","year":"2024","unstructured":"Wu, C., Li, Y., Xu, L., & Han, G. (2024). R\u00e9nyi entropy rate of stationary ergodic processes. IEEE Transactions on Information Theory, 70(1), 1\u201315.","journal-title":"IEEE Transactions on Information Theory"},{"key":"6872_CR82","doi-asserted-by":"crossref","unstructured":"Yamato, J., Ohya, J., & Ishii, K. (1992). Recognizing human action in time-sequential images using hidden Markov model. In Proceedings of the IEEE computer society conference on computer vision and pattern recognition (pp. 379\u2013385).","DOI":"10.1109\/CVPR.1992.223161"},{"key":"6872_CR83","doi-asserted-by":"crossref","DOI":"10.1201\/9781420010893","volume-title":"Hidden Markov models for time series: An introduction using R","author":"W Zucchini","year":"2009","unstructured":"Zucchini, W., & MacDonald, I. (2009). Hidden Markov models for time series: An introduction using R. Chapman & Hall."},{"key":"6872_CR84","doi-asserted-by":"crossref","unstructured":"Zuk, O., Kanter, I., & Domany, E. (2005). Asymptotics of the entropy rate for a hidden Markov process. In Proceedings of the data compression conference (pp. 173\u2013182).","DOI":"10.1109\/DCC.2005.18"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06872-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-025-06872-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06872-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T20:57:08Z","timestamp":1759870628000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-025-06872-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"references-count":84,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["6872"],"URL":"https:\/\/doi.org\/10.1007\/s10994-025-06872-4","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2025,9,16]]},"assertion":[{"value":"20 February 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 March 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no Conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This paper has been approved in terms of ethics.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Consent has been granted for the publication of this paper.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"232"}}