arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.07445cs.ITmath.IT
收藏

基于确定性记忆决策规则的二元假设检验

Binary Hypothesis Testing with Deterministic Finite-Memory Decision Rules

Tomer Berg, Ofer Shayevitz, Or Ordentlich

摘要:

本文研究有限记忆系统的二元假设检验问题。设$X_1,X_2,\ldots$是独立同分布的Bernoulli随机变量序列,期望$p$在$\mathcal{H}_0$下,$q$在$\mathcal{H}_1$下.考虑一个具有$S$状态的有限内存确定性机器,该机器每次都根据规则$M_n = f(M_{n-1},X_n)$更新其状态$M_n \in \{1,2,\ldots,S\}$,其中$f$是确定性时不变函数。假设我们让流程运行很长时间($n\rightarrow \infty)$),然后根据从状态空间到假设空间的某种映射来做出决策。本文的主要贡献是任何此类机器的贝叶斯错误概率$P_e$的下限。特别是,我们的研究结果表明,之间的比率的最大指数衰减率的$P_e$与$S$的确定性机器和随机的,可以成为无界的,补充了赫尔曼的结果。

英文摘要:

In this paper we consider the problem of binary hypothesis testing with finite memory systems. Let $X_1,X_2,\ldots$ be a sequence of independent identically distributed Bernoulli random variables, with expectation $p$ under $\mathcal{H}_0$ and $q$ under $\mathcal{H}_1$. Consider a finite-memory deterministic machine with $S$ states that updates its state $M_n \in \{1,2,\ldots,S\}$ at each time according to the rule $M_n = f(M_{n-1},X_n)$, where $f$ is a deterministic time-invariant function. Assume that we let the process run for a very long time ($n\rightarrow \infty)$, and then make our decision according to some mapping from the state space to the hypothesis space. The main contribution of this paper is a lower bound on the Bayes error probability $P_e$ of any such machine. In particular, our findings show that the ratio between the maximal exponential decay rate of $P_e$ with $S$ for a deterministic machine and for a randomized one, can become unbounded, complementing a result by Hellman.

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。

↑