基于经验观测统计量的通用分类中序贯性统一研究
A Unified Study on Sequentiality in Universal Classification with Empirically Observed Statistics
AI总结:
本文统一研究通用二元分类中的序贯性,在期望停止时间和第一类错误指数受通用性约束的框架下,刻画最优第二类错误指数并证明其上下界,从解析和数值上展示了序贯性相对固定长度方案的增益。
摘要:
在二元假设检验问题中,众所周知,采样中的序贯性能够消除两个错误指数之间的权衡,然而实现最优检验需要知道底层分布,例如 $P_0$ 和 $P_1$。在分布知识被来自相应分布的经验观测统计量所取代的场景中,当受到对所有可能的 $P_0,P_1$ 的通用性约束时,序贯性带来的增益尚不明确。本文通过对通用二元分类问题中序贯性的统一研究弥补了这一空白,其中通用性约束同时施加在期望停止时间和第一类错误指数上。第一类错误指数被要求对所有 $P_0,P_1$ 都达到一个预先设定的、依赖于分布的约束 $λ(P_0,P_1)$。在所提出的框架下,研究了不同的序贯设置,以便与固定长度对应方案进行公平比较。通过将这些序贯分类问题视为一般序贯复合假设检验问题的特例,刻画了最优第二类错误指数。具体而言,在受通用性约束的一般序贯复合假设检验问题中,证明了第二类错误指数的上界和下界,并给出了这些界重合的充分条件。随后相应地得到了序贯分类问题的结果。借助对最优错误指数的刻画,通过比较第一类指数约束 $λ$ 的代表性示例中的序贯和固定长度情形,从解析和数值两方面展示了序贯性的优势。
英文摘要:
In the binary hypothesis testing problem, it is well known that sequentiality in taking samples eradicates the trade-off between two error exponents, yet implementing the optimal test requires the knowledge of the underlying distributions, say $P_0$ and $P_1$. In the scenario where the knowledge of distributions is replaced by empirically observed statistics from the respective distributions, the gain of sequentiality is less understood when subject to universality constraints over all possible $P_0,P_1$. In this work, the gap is mended by a unified study on sequentiality in the universal binary classification problem, where the universality constraints are set on the expected stopping time as well as the type-I error exponent. The type-I error exponent is required to achieve a pre-set distribution-dependent constraint $λ(P_0,P_1)$ for all $P_0,P_1$. Under the proposed framework, different sequential setups are investigated so that fair comparisons can be made with the fixed-length counterpart. By viewing these sequential classification problems as special cases of a general sequential composite hypothesis testing problem, the optimal type-II error exponents are characterized. Specifically, in the general sequential composite hypothesis testing problem subject to universality constraints, upper and lower bounds on the type-II error exponent are proved, and a sufficient condition for which the bounds coincide is given. The results for sequential classification problems are then obtained accordingly. With the characterization of the optimal error exponents, the benefit of sequentiality is shown both analytically and numerically by comparing the sequential and the fixed-length cases in representative examples of type-I exponent constraint $λ$.
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。