arXiv subjects

Shohei Hidaka

Publications and source records attributed to Shohei Hidaka.

8 recordsLinked to original sources

arXiv2026

Algebraic Signatures for Structural Learning in Probability Tensors

Algebraic statistics characterizes statistical models through polynomial constraints, but it has mainly been used for analytically specified model classes. This paper studies the inverse problem: identifying probabilistic structure from vanishing binomials observed in empirical probability tensors. We treat the vanishing binomials of a toric model as its algebraic signature, and turn the ideal-variety correspondence of algebraic statistics into an operational procedure for structural learning that identifies a model by signature matching without parameter estimation. By restricting attention to a computationally tractable class of configuration matrices, which we call {\it the Kronecker-stack class}, we make these signatures explicitly enumerable. Within this class we define minimum invariant constraint (MIC) as the atomic unit characterizing each signature and generalizing the notion of independence. We tested this approach employing MICs on synthetic data as well as on corpus-scale real language data. The results suggested the utility of the method, revealing that the identified rank-one structures correspond to interpretable sets of words. These results open up a new avenue for applying algebraic statistics to computational linguistics.

stat.ML↗

arXiv2018

Clustering by latent dimensions

This paper introduces a new clustering technique, called {\em dimensional clustering}, which clusters each data point by its latent {\em pointwise dimension}, which is a measure of the dimensionality of the data set local to that point. Pointwise dimension is invariant under a broad class of transformations. As a result, dimensional clustering can be usefully applied to a wide range of datasets. Concretely, we present a statistical model which estimates the pointwise dimension of a dataset around the points in that dataset using the distance of each point from its $n^{\text{th}}$ nearest neighbor. We demonstrate the applicability of our technique to the analysis of dynamical systems, images, and complex human movements.

stat.ML↗

arXiv2018

Recursive Markov Process for Iterated Games with Markov Strategies

The dynamics in games involving multiple players, who adaptively learn from their past experience, is not yet well understood. We analyzed a class of stochastic games with Markov strategies in which players choose their actions probabilistically. This class is formulated as a $k^{\text{th}}$ order Markov process, in which the probability of choice is a function of $k$ past states. With a reasonably large $k$ or with the limit $k \to \infty$, numerical analysis of this random process is unfeasible. This study developed a technique which gives the marginal probability of the stationary distribution of the infinite-order Markov process, which can be constructed recursively. We applied this technique to analyze an iterated prisoner's dilemma game with two players who learn using infinite memory.

math.PR↗

arXiv2018

Polynomial algorithm for $k$-partition minimization of monotone submodular function

For a fixed $k$, this study considers $k$-partition minimization of submodular system $(V, f)$ with a finite set $V$ and symmetric submodular function $f: 2^{V} \mapsto \mathbb{R}$. Our algorithm uses the Queyranne's (1998) algorithm for 2-partition minimization which arises at each step of the recursive decomposition of subsets of the original $k$-partition minimization. We show that the computational complexity of this minimizer is $O(n^{3(k-1)})$.

math.OC↗

arXiv2018

Fast and exact search for the partition with minimal information loss

In analysis of multi-component complex systems, such as neural systems, identifying groups of units that share similar functionality will aid understanding of the underlying structures of the system. To find such a grouping, it is useful to evaluate to what extent the units of the system are separable. Separability or inseparability can be evaluated by quantifying how much information would be lost if the system were partitioned into subsystems, and the interactions between the subsystems were hypothetically removed. A system of two independent subsystems are completely separable without any loss of information while a system of strongly interacted subsystems cannot be separated without a large loss of information. Among all the possible partitions of a system, the partition that minimizes the loss of information, called the Minimum Information Partition (MIP), can be considered as the optimal partition for characterizing the underlying structures of the system. Although the MIP would reveal novel characteristics of the neural system, an exhaustive search for the MIP is numerically intractable due to the combinatorial explosion of possible partitions. Here, we propose a computationally efficient search to precisely identify the MIP among all possible partitions by exploiting the submodularity of the measure of information loss. Mutual information is one such submodular information loss functions, and is a natural choice for measuring the degree of statistical dependence between paired sets of random variables. By using mutual information as a loss function, we show that the search for MIP can be performed in a practical order of computational time for a reasonably large system. We also demonstrate that MIP search allows for the detection of underlying global structures in a network of nonlinear oscillators.

cs.IT↗

arXiv2014

General Type Token Distribution

We consider the problem of estimating the number of types in a corpus using the number of types observed in a sample of tokens from that corpus. We derive exact and asymptotic distributions for the number of observed types, conditioned upon the number of tokens and the latent type distribution. We use the asymptotic distributions to derive an estimator of the latent number of types and we validate this estimator numerically.

stat.ME↗

arXiv2014

On the Estimation of Pointwise Dimension

Our goal in this paper is to develop an effective estimator of fractal dimension. We survey existing ideas in dimension estimation, with a focus on the currently popular method of Grassberger and Procaccia for the estimation of correlation dimension. There are two major difficulties in estimation based on this method. The first is the insensitivity of correlation dimension itself to differences in dimensionality over data, which we term "dimension blindness". The second comes from the reliance of the method on the inference of limiting behavior from finite data. We propose pointwise dimension as an object for estimation in response to the dimension blindness of correlation dimension. Pointwise dimension is a local quantity, and the distribution of pointwise dimensions over the data contains the information to which correlation dimension is blind. We use a "limit-free" description of pointwise dimension to develop a new estimator. We conclude by discussing potential applications of our estimator as well as some challenges it raises.

physics.data-an↗

arXiv2012

Characterizing Multivariate Information Flows

One of the crucial steps in scientific studies is to specify dependent relationships among factors in a system of interest. Given little knowledge of a system, can we characterize the underlying dependent relationships through observation of its temporal behaviors? In multivariate systems, there are potentially many possible dependent structures confusable with each other, and it may cause false detection of illusory dependency between unrelated factors. The present study proposes a new information-theoretic measure with consideration to such potential multivariate relationships. The proposed measure, called multivariate transfer entropy, is an extension of transfer entropy, a measure of temporal predictability. In the simulations and empirical studies, we demonstrated that the proposed measure characterized the latent dependent relationships in unknown dynamical systems more accurately than its alternative measure.

cs.IT↗