In this paper we consider the problem of estimating a Bernoulli parameter using finite memory. Let $X_1,X_2,\ldots$ be a sequence of independent identically distributed Bernoulli random variables with expectation $\theta$, where $\theta \in [0,1]$. 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 the machine outputs an estimate at each time point according to some fixed mapping from the state space to the unit interval. The quality of the estimation procedure is measured by the asymptotic risk, which is the long-term average of the instantaneous quadratic risk. The main contribution of this paper is an upper bound on the smallest worst-case asymptotic risk any such machine can attain. This bound coincides with a lower bound derived by Leighton and Rivest, to imply that $\Theta(1/S)$ is the minimax asymptotic risk for deterministic $S$-state machines. In particular, our result disproves a longstanding $\Theta(\log S/S)$ conjecture for this quantity, also posed by Leighton and Rivest.
翻译:在本文中, 我们考虑使用有限内存来估算伯努利参数的问题 。 请让 $X_ 1, X_ 2,\ldots 是一个单独分布的相同分布的伯努利随机变量序列, 期望为$\theta$, 其中$\theta = $ = $ [0, 1$] 。 考虑一个使用 $S 状态的限量确定性机器, 以 1, 2,\ldots 来更新其状态 $M_ n = f( M ⁇ n-1}, X_ n) 。 美元是独立的, 美元是相同的 美元 。 假设机器在每一时间点根据从州空间到单位间隔的固定映射结果做出一个估算。 估计程序的质量以负数风险衡量, 这是瞬间四重风险的长期平均值 。 本文的主要贡献是最小的最坏的情况, 任何这类机器都能达到的最坏的情况风险 。 这个绑定值中, 也代表着我们最下值的货币 $ 。