PulseAugur
中
实时 12:45:50
English(EN) Sample Complexity and Decision-Theoretic Guarantees for Bayesian Model Averaging over Decision Trees with Catalan-Exponential Priors

决策树的贝叶斯模型平均理论详解

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员发表了一篇论文，详细介绍了决策树上贝叶斯模型平均（BMA）的样本复杂度和决策论保证。该工作侧重于确定BMA权重何时提供足够的信息来证明利用平均分布的合理性。该研究为理性承诺阈值提供了一个完整的非渐近理论，特别是针对具有Dirichlet-Multinomial叶模型和Catalan-指数树大小先验的贝叶斯决策树。 AI

影响 为决策树模型提供了理论基础，有可能提高其样本效率和决策能力。

排序理由 该集群包含一篇详细介绍机器学习技术理论保证的学术论文。

在 arXiv stat.ML 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv stat.ML TIER_1 English(EN) · Livija Jakaite, Vitaly Schetinin ·

    Catalan-Exponential先验下贝叶斯模型平均在决策树上的样本复杂度和决策理论保证

    arXiv:2606.01340v1 Announce Type: cross Abstract: We ask: when do Bayesian model averaging (BMA) weights over decision trees carry sufficient epistemic information to justify committed exploitation of the averaging distribution? We answer this question in closed form for Bayesian…

  2. arXiv stat.ML TIER_1 English(EN) · Vitaly Schetinin ·

    Sample Complexity and Decision-Theoretic Guarantees for Bayesian Model Averaging over Decision Trees with Catalan-Exponential Priors

    We ask: when do Bayesian model averaging (BMA) weights over decision trees carry sufficient epistemic information to justify committed exploitation of the averaging distribution? We answer this question in closed form for Bayesian decision trees (BDTs) with Dirichlet-Multinomial …

相关实体

相关话题