Akira Kamatsuka

Akira Kamatsuka, Takahiro Yoshida

We study conditional entropy frameworks based on the Kolmogorov--Nagumo (KN) mean. First, we introduce $(η, ψ)$-KN averaging (\texttt{EPKNAVG}), a KN-mean extension of the $η$-averaging (\texttt{EAVG}) framework for $(η, F)$-entropy, and prove that, under suitable concavification conditions, it is equivalent to \texttt{EAVG}. Second, motivated by generalized $g$-vulnerability, we propose a new framework of generalized $g$-conditional entropies. We show that this framework captures conditional entropies beyond the scope of \texttt{EAVG}-type representations. In particular, there exists $α\in(0,1)\cup(1,\infty)$ such that the Augustin--Csisz{\' a}r conditional entropy $H_α^{\mathrm{C}}(X|Y)$ cannot be represented by any $(η,F)$-entropy satisfying \texttt{EAVG}, whereas it is represented within the proposed framework. We further derive sufficient conditions for the proposed generalized $g$-conditional entropies to satisfy conditioning reduces entropy (\texttt{CRE}) and the data-processing inequality (\texttt{DPI}).

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--variance-type decompositions for Bregman divergences, we consider two natural loss functions, $D_φ(θ,\hatθ)$ and $D_φ(\hatθ,θ)$, and their corresponding notions of unbiasedness. We show that the latter formulation reduces to the classical setting, whereas the former yields a different framework in which unbiasedness is characterized in the dual space induced by $\nablaφ$. For the nontrivial case, we establish analogs of the Rao--Blackwell and Lehmann--Scheff{é} theorems, providing a systematic construction of type-I Bregman UMVUEs.

Yuta Nakahara, Shota Saito, Akira Kamatsuka et al.

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 machine learning. On the other hand, such hierarchical expressive capability causes a problem in tree selection to avoid overfitting. One unified approach to solve this is a Bayesian approach, on which the rooted tree is regarded as a random variable and a direct loss function can be assumed on the selected model or the predicted value for a new data point. However, all the previous studies on this approach are based on the probability distribution on full trees, to the best of our knowledge. In this paper, we propose a generalized probability distribution for any rooted trees in which only the maximum number of child nodes and the maximum depth are fixed. Furthermore, we derive recursive methods to evaluate the characteristics of the probability distribution without any approximations.

Yuta Nakahara, Shota Saito, Akira Kamatsuka et al.

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 machine learning. In most of these cases, the full rooted tree is not a random variable; as such, model selection to avoid overfitting becomes problematic. A method to solve this problem is to assume a prior distribution on the full rooted trees. This enables the optimal model selection based on the Bayes decision theory. For example, by assigning a low prior probability to a complex model, the maximum a posteriori estimator prevents the selection of the complex one. Furthermore, we can average all the models weighted by their posteriors. In this paper, we propose a probability distribution on a set of full rooted trees. Its parametric representation is suitable for calculating the properties of our distribution using recursive functions, such as the mode, expectation, and posterior distribution. Although such distributions have been proposed in previous studies, they are only applicable to specific applications. Therefore, we extract their mathematically essential components and derive new generalized methods to calculate the expectation, posterior distribution, etc.