<?xml version='1.0' encoding='UTF-8'?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
  <responseDate>2026-03-08T01:22:05Z</responseDate>
  <request metadataPrefix="oai_dc" verb="GetRecord" identifier="oai:ipsj.ixsq.nii.ac.jp:00234899">https://ipsj.ixsq.nii.ac.jp/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:ipsj.ixsq.nii.ac.jp:00234899</identifier>
        <datestamp>2025-01-19T09:40:37Z</datestamp>
        <setSpec>1164:2735:11468:11669</setSpec>
      </header>
      <metadata>
        <oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns="http://www.w3.org/2001/XMLSchema" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
          <dc:title>ゼロ過剰データに対するベイズ符号に基づく因果構造の学習</dc:title>
          <dc:title>Causal Structure Learning for Zero-Inﬂated Data Based on Bayes Code</dc:title>
          <dc:creator>小林, 将理</dc:creator>
          <dc:creator>久保木, 優太</dc:creator>
          <dc:creator>松島, 慎</dc:creator>
          <dc:creator>Masatoshi, Kobayashi</dc:creator>
          <dc:creator>Yuta, Kuboki</dc:creator>
          <dc:creator>Shin, Matsushima</dc:creator>
          <dc:subject>情報論的学習理論と機械学習2</dc:subject>
          <dc:description>本研究では，zero inﬂated な多変量カウントデータに対して，変数間の因果関係を統計的に推論する手法を提案する．既存研究の Choi et al. (2020) が提案した ZIPBN は，因果に Zero-Inﬂated Poisson (ZIP) モデルを仮定し，因果グラフの識別可能性を利用した手法である．我々は ZIPBN を情報理論的観点から再解釈し，アルゴリズム的独立性の仮定の下でコルモゴロフ複雑性の近似としてのベイズ符号を最小にする因果モデルの選択問題として定式化できることを示す．提案手法の有効性を人工データで検証した．</dc:description>
          <dc:description>In this paper, we propose a method for statistically inferring causal relationships between variables in zero-inﬂated multivariate count data. The Zero-Inﬂated Poisson Bayesian Network (ZIPBN) model proposed by Choi et al. (2020) assumes a Zero-Inﬂated Poisson (ZIP) model for causal mechanism and utilizes the identiﬁability of causal graphs. We reinterpret ZIPBN from an information-theoretic perspective, demonstrating that it can be formulated as a problem of selecting a causal model that minimizes the Bayes Code as an approximation of Kol- mogorov complexity, under the assumption of algorithmic independence of conditionals. The eﬀectiveness of our approach is validated with synthetic data.</dc:description>
          <dc:description>technical report</dc:description>
          <dc:publisher>情報処理学会</dc:publisher>
          <dc:date>2024-06-13</dc:date>
          <dc:format>application/pdf</dc:format>
          <dc:identifier>研究報告数理モデル化と問題解決（MPS）</dc:identifier>
          <dc:identifier>12</dc:identifier>
          <dc:identifier>2024-MPS-148</dc:identifier>
          <dc:identifier>1</dc:identifier>
          <dc:identifier>6</dc:identifier>
          <dc:identifier>2188-8833</dc:identifier>
          <dc:identifier>AN10505667</dc:identifier>
          <dc:identifier>https://ipsj.ixsq.nii.ac.jp/record/234899/files/IPSJ-MPS24148012.pdf</dc:identifier>
          <dc:language>jpn</dc:language>
        </oai_dc:dc>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
