11 citations · 39 across the 20 of their papers we have counts for
21 papers
Prediction Algorithms Achieving Bayesian Decision Theoretical Optimality Based on Decision Trees as Data Observation Processes
Yuta Nakahara, Shota Saito, Naoki Ichijo +2
In the field of decision trees, most previous studies have difficulty ensuring the statistical optimality of a prediction of new data and suffer from overfitting because trees are…
Batch Updating of a Posterior Tree Distribution over a Meta-Tree
Yuta Nakahara, Toshiyasu Matsushima
Previously, we proposed a probabilistic data generation model represented by an unobservable tree and a sequential updating method to calculate a posterior distribution over a set…
An Algorithm for Computing the Stratonovich's Value of Information
Akira Kamatsuka, Takahiro Yoshida, Koki Kazama +1
We propose an algorithm for computing Stratonovich's value of information (VoI) that can be regarded as an analogue of the distortion-rate function. We construct an alternating opt…
Stochastic 2D Signal Generative Model with Wavelet Packets Basis Regarded as a Random Variable and Bayes Optimal Processing
Ryohei Oka, Yuta Nakahara, Toshiyasu Matsushima
This study deals with two-dimensional (2D) signal processing using the wavelet packet transform. When the basis is unknown the candidate of basis increases in exponential order wit…
A Generalization of the Stratonovich's Value of Information and Application to Privacy-Utility Trade-off
Akira Kamatsuka, Takahiro Yoshida, Toshiyasu Matsushima
The Stratonovich's value of information (VoI) is quantity that measure how much inferential gain is obtained from a perturbed sample under information leakage constraint. In this p…
Probability Distribution on Rooted Trees
Yuta Nakahara, Shota Saito, Akira Kamatsuka +1
The hierarchical and recursive expressive capability of rooted trees is applicable to represent statistical models in various areas, such as data compression, image processing, and…
Probability Distribution on Full Rooted Trees
Yuta Nakahara, Shota Saito, Akira Kamatsuka +1
The recursive and hierarchical structure of full rooted trees is applicable to represent statistical models in various areas, such as data compression, image processing, and machin…
A Stochastic Model for Block Segmentation of Images Based on the Quadtree and the Bayes Code for It
Yuta Nakahara, Toshiyasu Matsushima
In information theory, lossless compression of general data is based on an explicit assumption of a stochastic generative model on target data. However, in lossless image compressi…
An Efficient Bayes Coding Algorithm for the Non-Stationary Source in Which Context Tree Model Varies from Interval to Interval
Koshi Shimada, Shota Saito, Toshiyasu Matsushima
The context tree source is a source model in which the occurrence probability of symbols is determined from a finite past sequence, and is a broader class of sources that includes…
Theoretical Analysis of the Advantage of Deepening Neural Networks
Yasushi Esaki, Yuta Nakahara, Toshiyasu Matsushima
We propose two new criteria to understand the advantage of deepening neural networks. It is important to know the expressivity of functions computable by deep neural networks in or…
Evaluation of Error Probability of Classification Based on the Analysis of the Bayes Code: Extension and Example
Shota Saito, Toshiyasu Matsushima
Suppose that we have two training sequences generated by parametrized distributions and , where and are unknown true parameters. Given training seque…
Covariance Evolution for Spatially "Mt. Fuji" Coupled LDPC Codes
Yuta Nakahara, Toshiyasu Matsushima
A spatially "Mt. Fuji" coupled low-density parity check (LDPC) ensemble is a modified version of the original spatially coupled (SC) LDPC ensemble. Its desirable properties are fir…
Distributed Stochastic Gradient Descent Using LDGM Codes
Shunsuke Horii, Takahiro Yoshida, Manabu Kobayashi +1
We consider a distributed learning problem in which the computation is carried out on a system consisting of a master node and multiple worker nodes. In such systems, the existence…
Non-Asymptotic Fundamental Limits of Guessing Subject to Distortion
Shota Saito, Toshiyasu Matsushima
This paper investigates the problem of guessing subject to distortion, which was introduced by Arikan and Merhav. While the primary concern of the previous study was asymptotic ana…
A Novel Scheme to Improve Lossless Image Coders by Explicit Description of Generative Model Classes
Yuta Nakahara, Toshiyasu Matsushima
In this study, we propose a novel scheme for systematic improvement of lossless image compression coders from the point of view of the universal codes in information theory. In the…
Cumulant Generating Function of Codeword Lengths in Variable-Length Lossy Compression Allowing Positive Excess Distortion Probability
Shota Saito, Toshiyasu Matsushima
This paper considers the problem of variable-length lossy source coding. The performance criteria are the excess distortion probability and the cumulant generating function of code…
Variable-Length Intrinsic Randomness Allowing Positive Value of the Average Variational Distance
Jun Yoshizawa, Shota Saito, Toshiyasu Matsushima
This paper considers the problem of variable-length intrinsic randomness. We propose the average variational distance as the performance criterion from the viewpoint of a dual rela…
Variable-Length Lossy Compression Allowing Positive Overflow and Excess Distortion Probabilities
Shota Saito, Hideki Yagi, Toshiyasu Matsushima
This paper investigates the problem of variable-length lossy source coding allowing a positive excess distortion probability and an overflow probability of codeword lengths. Novel…
Linear Programming Decoding of Binary Linear Codes for Symbol-Pair Read Channels
Shunsuke Horii, Toshiyasu Matsushima, Shigeichi Hirasawa
In this paper, we develop a new decoding algorithm of a binary linear codes for symbol-pair read channels. Symbol-pair read channel has recently been introduced by Cassuto and Blau…
Information Spectrum Approach to Overflow Probability of Variable-Length Codes with Conditional Cost Function
Ryo Nomura, Toshiyasu Matsushima
Lossless variable-length source coding with unequal cost function is considered for general sources. In this problem, the codeword cost instead of codeword length is important. The…
Bayesian Forecasting of WWW Traffic on the Time Varying Poisson Model
Daiki Koizumi, Toshiyasu Matsushima, Shigeichi Hirasawa
Traffic forecasting from past observed traffic data with small calculation complexity is one of important problems for planning of servers and networks. Focusing on World Wide Web…