### Shota Saito (Faculty of Informatics, Gunma University )

#### Research Field

Information Theory and Its Application to Machine Learning

#### Biography

B.E. degree in Department of Applied Mathematics, Waseda University in Mar. 2013

M.E. and Doctor of Engineering degrees in Department of Pure and Applied Mathematics, Waseda University in Mar. 2015 and Mar. 2018

Assistant Professor at Department of Applied Mathematics, Waseda University from Apr. 2018 to Mar. 2021

Associate Professor, Faculty of Informatics, Gunma University, from Apr. 2021

#### Research Achievement

≪Journal≫

Haruka Murayama,Cluster's Number Free Bayes Prediction of General Framework on Mixture of Regression Models,Journal of Statistical Theory and Applications,Vol.20, issue 3, pp.425-449,2021

Yuta Nakahara,Probability Distribution on Full Rooted Trees,Entropy,24(3) 328-346,2022

Shota Saito,Upper Bound on Privacy-Utility Tradeoff Allowing Positive Excess Distortion Probability,IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences,E105.A(3) 425-427,2022

Shota Saito,Non-Asymptotic Bounds of Cumulant Generating Function of Codeword Lengths in Variable-Length Lossy Compression,IEEE Transactions on Information Theory,vol.69, no.4, pp.2113-2119,2023

Shota Saito,Evaluation of the Bayes Code from Viewpoints of the Distribution of Its Codeword Lengths,IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences,vol.E98-A, no.12, pp. 2407–2414,2015

Shota Saito,Threshold of Overflow Probability Using Smooth Max-Entropy in Lossless Fixed-to-Variable Length Source Coding for General Sources,IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences,vol.E99-A, no.12, pp.2286-2290,2016

Shota Saito,Second-Order Achievable Rate Region of Slepian-Wolf Coding Problem in Terms of Smooth Max-Entropy for General Sources,IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences,vol.E99-A, no.12, pp.2275-2280,2016

Shota Saito,Evaluation of Overflow Probability of Bayes Code in Moderate Deviation Regime,IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences,vol.E100-A, no.12, pp.2728-2731,2017

Yuta Nakahara,Spatially ``Mt. Fuji'' Coupled LDPC Codes,IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences,vol.E100-A, no.12, pp.2594-2606,2017

Junki Yamaguchi,A Note on Mixed Level Experimental Designs Using Augmented Orthogonal Arrays,IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences,vol.J103-A, No.1, pp.-, Jan. 2020.,2020

Jun Yoshizawa,Variable-Length Intrinsic Randomness on Two Performance Criteria based on Variational Distance,IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences,E102-A(12), pp.1642-1650,2019

Nao Dobashi,Meta-Tree Random Forest: Probabilistic Data-Generative Model and Bayes Optimal Prediction,Entropy,vol. 23, no. 6, 768,2021

≪International Conference≫

Shota Saito,Evaluation of Error Probability of Classification Based on the Analysis of the Bayes Code,2020 IEEE International Symposium on Information Theory,pp. 2510-2514,2020

Shota Saito,On Two Information Quantities Relating Two Distortion Balls,Proceedings of 2020 International Symposium on Information Theory and Its Applications,pp. 16-20,2020

Shota Saito,Evaluation of Error Probability of Classification Based on the Analysis of the Bayes Code: Extension and Example,Proceedings of 2021 IEEE International Symposium on Information Theory (ISIT),,2021

Koshi Shimada,An Efficient Bayes Coding Algorithm for the Non-Stationary Source in Which Context Tree Model Varies from Interval to Interval,Proceedings of 2021 IEEE Information Theory Workshop (ITW),,2021

Yuta Nakahara,Probability Distribution on Rooted Trees,2022 IEEE International Symposium on Information Theory,,2022

Shota Saito,On Meta-Bound for Lower Bounds of Bayes Risk,2022 IEEE International Symposium on Information Theory,,2022

Taisuke Ishiwatari,Bayes Optimal Estimation and Its Approximation Algorithm for Difference with and without Treatment under URLC Model,2022 International Symposium on Information Theory and Its Applications,,2022

Shota Saito,Evaluation of the Minimum Overflow Threshold of Bayes Codes for a Markov Source,Proceedings of the 2014 International Symposium on Information Theory and Its Applications,pp.211–215,2014

Shota Saito,Fundamental Limit and Pointwise Asymptotics of the Bayes Code for Markov Sources,Proceedings of 2015 IEEE International Symposium on Information Theory,pp.1986–1990, Hong Kong, China,2015

Shota Saito,Evaluation of Overflow Probability of Bayes Code in Moderate Deviation Regime,Proceedings of the 2016 International Symposium on Information Theory and Its Applications,pp.1-5,2016

Shota Saito,Threshold of Overflow Probability in Terms of Smooth Max-Entropy for Variable-Length Compression Allowing Errors,Proceedings of the 2016 International Symposium on Information Theory and Its Applications,pp.21-25,2016

Yuta Nakahara,Spatially “Mt. Fuji” Coupled LDPC Codes,Proceedings of the 2016 International Symposium on Information Theory and Its Applications,pp.201-205,2016

Shota Saito,Variable-Length Lossy Compression Allowing Positive Overflow and Excess Distortion Probabilities,Proceedings of 2017 IEEE International Symposium on Information Theory,pp.1568-1572, Aachen, Germany,2017

Shota Saito,Cumulant Generating Function of Codeword Lengths in Variable-Length Lossy Compression Allowing Positive Excess Distortion Probability,Proceedings of 2018 IEEE International Symposium on Information Theory,pp.652-656,2018

Jun Yoshizawa,Variable-Length Intrinsic Randomness Allowing Positive Value of the Average Variational Distance,2018 International Symposium on Information Theory and Its Applications,pp.354--358,2018

Shota Saito,New Results on Variable-Length Lossy Compression Allowing Positive Overflow and Excess Distortion Probabilities,Proceedings of International Symposium on Information Theory and Its Applications (ISITA),pp.359--363,2018

Kai Asaba,Bayesian Independent Component Analysis under Hierarchical Model on Independent Components,Proceedings of Asia-Pacific Signal and Information Processing Association Annual Summit and Conference,pp.959--962,2018

Shota Saito,Non-Asymptotic Fundamental Limits of Guessing Subject to Distortion,2019 IEEE International Symposium on Information Theory,pp.652-656,2019

≪Conference≫

Nao Dobashi,Probabilistic Data Generating Process on Tree Structure Model: Bayes Optimal Prediction and Sub-Optimal Algorithm,,,2020

Koshi Shimada,An Efficient Bayes Coding Algorithm for the Source Based on Context Tree Models that Vary from Section to Section,,vol.120, no.410, IT2020-115, pp.19-24,2021

Shota Saito,Non-asymptotic converse theorem on the overflow probability of variable-to-fixed length codes,,,2021

Yuta Nakahara,Probability Distribution on Full Rooted Trees,,,2021

Shota Saito,A Refined Analysis of Merhav and Ziv's Bayesian Approach for Classification of Markov Sources,,,2021

Shota Saito,On Bayesian Approach for Classification of Context Tree Model,,,2022

Shota SAITO,Evaluation of Minimum Overflow Threshold for Bayes Codes,Proceedings of the 36th Symposium on Information Theory and its Applications,pp.24-29,2013

Shota SAITO,Asymptotic Normality and LIL of the Codeword Length of Bayes Codes for Stationary Ergodic Markov Sources,Proceedings of the 37th Symposium on Information Theory and its Applications,pp.28–33,2014

Shota Saito,Another Representation on the Second-Order Achievable Rate Region of Slepian-Wolf Coding Problem for General Sources,,vol.114, no.470, IT2014-87, pp.159–165,2015

,Variations of the Strong Converse Theorem on the Intrinsic Randomness Problem for General Sources,,vol.115, no. 137, IT2015-17, pp.1-6,2015

Yuta Nakahara,A Study on Message Passing Algorithm for Counting Short Cycles in Sparse Bipartite Graphs,IEICE Technical Report,vol.115, no.395, IT2015-50, pp.13-18,2016

,A Note on the Optimal Data Prediction under Bayes Criterion for Multidimensional Linear Regression Models Assuming Latent Variables,,vol.115, no.414, PRMU2015-131, pp.269-273,2016

,A Note on the Computational Complexity Reduction Method of the Optimal Prediction under Bayes Criterion in Semi-Supervised Learning,,vol.115, no.414, PRMU2015-131, pp.275-280,2016

Yuta NAKAHARA,Universality of Spatially Coupled Punctured LDPC Codes for Decode-and-Forward in Erasure Relay Channels,Proceedings of the 37th Symposium on Information Theory and its Applications,pp.319-324,2014

Kota Kubo,A Note on Attack Against Nonlinear Combiner Generator Using Sum - Product Algorithm,,vol.114, no.306, IBISML2014-83, pp.357-364,2014

Shota Saito,Variable-Length Lossy Compression Allowing Positive Overflow and Excess Distortion Probabilities,,pp.164-169,2016

Jun Yoshizawa,Variable-Length Intrinsic Randomness Problem Allowing Non-Vanishing Underflow Probability,,vol. 117, no. 120, IT2017-29, pp. 73-78,2017

Hirokazu Kono,Evaluation of Bayes Predictive Distributions under Unknown Parametric Models on Misspecified Models,,vol. 117, no. 487, IT2017-103, pp. 1-6,2018

Kai Asaba,Bayesian Independent Component Analysis under Hierarchical Model on Latent Variables,,vol. 117, no. 475, IBISML2017-97, pp. 49-53,2018

Shota Saito,On Information Spectrum and Its Tail Probability,The IEICE General Conference,,2018

Haruka Murayama,Bayes Optimal Prediction and Its Approximative Algorithm on Model Including Cluster Explanatory Variables and Regression Explanatory Variables,,vol. 119, no. 149, IT2019-16, pp. 5-10,2019

Nao Dobashi,Bayes Optimal Classification on Decision Tree Model and Its Approximative Algorithm Using Ensemble Learning,,vol. 119, no. 149, IT2019-17, pp. 11-16,2019

Shota Saito,Non-Asymptotic and Asymptotic Fundamental Limits of Guessing Subject to Distortion,,,2018

Shota Saito,Evaluation of Error Probability of Classification Based on the Analysis of the Bayes Code,Proceedings of 2019 Symposium on Information Theory and Its Applications (SITA2019),pp.195--197,2019

≪Doctor Thesis≫

Shota Saito,Non-Asymptotic and Asymptotic Analyses of Source Coding: An Approach from the Viewpoint of the Overflow Probability,Ph.D. dissertation, Waseda University,,2018

≪etc≫

Awards:

・ISITA 2016, IEEE IT Society Japan Chapter Young Researcher Best Paper Award

・ISITA 2016, Student Paper Award

・Waseda University Azusa Ono Memorial Award (Academic), 2016

・Symposium on Information Theory and its Applications Young Researcher Paper Award, 2018

・Waseda University Teaching Award, 2019