Memory Complexity of Estimating Entropy and Mutual Information

๐Ÿ“… 2024-06-10
๐Ÿ›๏ธ IEEE Transactions on Information Theory
๐Ÿ“ˆ Citations: 1
โœจ Influential: 0
๐Ÿ“„ PDF

career value

285K/year
๐Ÿค– AI Summary
This paper investigates entropy and mutual information estimation for streaming discrete data under finite memory constraints: given an i.i.d. sequence, how to estimate the distributionโ€™s entropy using an $S$-state finite automaton with probability at least $1-delta$ and additive error at most $varepsilon$, and what is the tight characterization of the minimal $S$? Methodologically, it establishes the first asymptotically tight memory complexity bound for entropy estimation, proposes a randomized finite-state algorithm based on approximate counting and bias correction, and reduces the lower-bound analysis to uniformity testing. The theoretical contributions are: (i) a tight upper bound of $Oig(n(log n)^4/(varepsilon^2delta)ig)$ and a tight lower bound of $Omegaig(max{n,, log n / varepsilon}ig)$ on memory complexity for entropy estimation; and (ii) the first complete characterization of memory complexity for mutual information estimation, extending the results to that setting.

Technology Category

Application Category

๐Ÿ“ Abstract
We observe an infinite sequence of independent identically distributed random variables $X_1,X_2,ldots$ drawn from an unknown distribution $p$ over $[n]$, and our goal is to estimate the entropy $H(p)=-mathbb{E}[log p(X)]$ within an $varepsilon$-additive error. To that end, at each time point we are allowed to update a finite-state machine with $S$ states, using a possibly randomized but time-invariant rule, where each state of the machine is assigned an entropy estimate. Our goal is to characterize the minimax memory complexity $S^*$ of this problem, which is the minimal number of states for which the estimation task is feasible with probability at least $1-delta$ asymptotically, uniformly in $p$. Specifically, we show that there exist universal constants $C_1$ and $C_2$ such that $ S^* leq C_1cdotfrac{n (log n)^4}{varepsilon^2delta}$ for $varepsilon$ not too small, and $S^* geq C_2 cdot max {n, frac{log n}{varepsilon}}$ for $varepsilon$ not too large. The upper bound is proved using approximate counting to estimate the logarithm of $p$, and a finite memory bias estimation machine to estimate the expectation operation. The lower bound is proved via a reduction of entropy estimation to uniformity testing. We also apply these results to derive bounds on the memory complexity of mutual information estimation.
Problem

Research questions and friction points this paper is trying to address.

Estimating entropy within additive error using finite-state machines
Characterizing minimax memory complexity for entropy estimation
Deriving bounds for mutual information estimation memory complexity
Innovation

Methods, ideas, or system contributions that make the work stand out.

Finite-state machine for entropy estimation
Approximate counting for logarithm estimation
Finite memory bias estimation machine
T
Tomer Berg
O
O. Ordentlich
O
O. Shayevitz