arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.02271stat.MEcs.LGeess.SP
收藏

通过马尔可夫链的 de Finetti 定理将保形预测扩展至具有精确有效性的隐马尔可夫模型

Extending Conformal Prediction to Hidden Markov Models with Exact Validity via de Finetti's Theorem for Markov Chains

Tippie College of Business, University of Iowa(爱荷华大学蒂皮商学院);Pacific Northwest National Laboratory(太平洋西北国家实验室);Palo Alto Networks(帕洛阿尔托网络)

Buddhika Nettasinghe, Samrat Chatterjee, Ramakrishna Tipireddy, Mahantesh Halappanavar

AI总结:

本文将保形预测推广至隐马尔可夫模型,利用马尔可夫链的 de Finetti 定理将不可交换数据划分为可交换块,在保留理论保证的同时将不可交换性转化为提升性能的优势。

摘要:

保形预测是一种广泛使用的方法,用于在可交换性假设(例如 IID 数据)下量化分类器的不确定性。我们将保形预测推广到可交换性假设不成立的隐马尔可夫模型(HMM)框架中。该方法的关键思想是利用 Diaconis 和 Freedman(1980)发现的马尔可夫链的 de Finetti 定理,将来自 HMM 的不可交换马尔可夫数据划分为可交换的块。这些可交换块的排列被视为对来自 HMM 的观测马尔可夫数据的随机化。所提出的方法可证明在可交换和马尔可夫设置下均保留了经典保形预测框架提供的所有理想理论保证。特别是,虽然马尔可夫样本引入的不可交换性构成了对经典保形预测关键假设的违反,但所提出的方法将其视为一种可加以利用以进一步提升性能的优势。提供了补充理论结论的详细数值和经验结果,以说明所提出方法的实际可行性。

英文摘要:

Conformal prediction is a widely used method to quantify the uncertainty of a classifier under the assumption of exchangeability (e.g., IID data). We generalize conformal prediction to the Hidden Markov Model (HMM) framework where the assumption of exchangeability is not valid. The key idea of the proposed method is to partition the non-exchangeable Markovian data from the HMM into exchangeable blocks by exploiting the de Finetti's Theorem for Markov Chains discovered by Diaconis and Freedman (1980). The permutations of the exchangeable blocks are viewed as randomizations of the observed Markovian data from the HMM. The proposed method provably retains all desirable theoretical guarantees offered by the classical conformal prediction framework in both exchangeable and Markovian settings. In particular, while the lack of exchangeability introduced by Markovian samples constitutes a violation of a crucial assumption for classical conformal prediction, the proposed method views it as an advantage that can be exploited to improve the performance further. Detailed numerical and empirical results that complement the theoretical conclusions are provided to illustrate the practical feasibility of the proposed method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑