1 citations · 1 across the 13 of their papers we have counts for
14 papers
Kolmogorov--Nagumo Mean Frameworks for Conditional Entropy
Akira Kamatsuka, Takahiro Yoshida
This study focuses on conditional entropy frameworks based on the Kolmogorov--Nagumo (KN) mean. First, -KN averaging (\texttt{EPKNAVG}), a KN-mean extension of the -aver…
UMVUE-Type Estimators under Bregman Losses
Akira Kamatsuka, Shun Watanabe
We study unbiased estimation under Bregman losses and develop an extension of the classical theory of uniformly minimum variance unbiased estimators (UMVUEs). Exploiting bias--vari…
A Generalized Information Bottleneck Method: A Decision-Theoretic Perspective
Akira Kamatsuka, Takahiro Yoshida
The information bottleneck (IB) method seeks a compressed representation of data that preserves information relevant to a target variable for prediction while discarding irrelevant…
A Generalized Leakage Interpretation of Alpha-Mutual Information
Akira Kamatsuka, Takahiro Yoshida
This paper presents a unified interpretation of -mutual information (-MI) in terms of generalized -leakage. Specifically, we present a novel interpretation of -MI withi…
Several Representations of -Mutual Information and Interpretations as Privacy Leakage Measures
Akira Kamatsuka, Takashiro Yoshida
In this paper, we present several novel representations of -mutual information (-MI) in terms of R{\' e}nyi divergence and conditional R{\' e}nyi entropy. The representations…
A Variational Characterization of -Mutual Information and its Application to Computing -Capacity
Akira Kamatsuka, Koki Kazama, Takahiro Yoshida
-mutual information (-MI) is a wide class of information leakage measures, where is a pair of monotonically increasing function and a concave function , whi…
A New Algorithm for Computing -Capacity
Akira Kamatsuka, Koki Kazama, Takahiro Yoshida
The problem of computing -capacity for is equivalent to that of computing the correct decoding exponent. Various algorithms for computing them have been proposed, such as…
Alternating Optimization Approach for Computing -Mutual Information and -Capacity
Akira Kamatsuka, Koki Kazama, Takahiro Yoshida
This study presents alternating optimization (AO) algorithms for computing -mutual information (-MI) and -capacity based on variational characterizations of -MI using a…
New Algorithms for Computing Sibson Capacity and Arimoto Capacity
Akira Kamatsuka, Yuki Ishikawa, Koki Kazama +1
The Sibson and Arimoto capacity, which are based on the Sibson and Arimoto mutual information (MI) of order α, respectively, are well-known generalizations of the channel capacity…
On Hypothesis Testing via a Tunable Loss
Akira Kamatsuka
We consider a problem of simple hypothesis testing using a randomized test via a tunable loss function proposed by Liao \textit{et al}. In this problem, we derive results that corr…
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…
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…