Probabilistic counting algorithms for data base applications
Journal of Computer and System Sciences
Estimating a probability using finite memory
IEEE Transactions on Information Theory
Learning regular sets from queries and counterexamples
Information and Computation
The space complexity of approximating the frequency moments
Journal of Computer and System Sciences
External memory algorithms
Counting large numbers of events in small registers
Communications of the ACM
An Approximate L1-Difference Algorithm for Massive Data Streams
SIAM Journal on Computing
Universal Finite Memory Machines for Coding Binary Sequences
DCC '00 Proceedings of the Conference on Data Compression
R-max - a general polynomial time algorithm for near-optimal reinforcement learning
The Journal of Machine Learning Research
Optimal approximations of the frequency moments of data streams
Proceedings of the thirty-seventh annual ACM symposium on Theory of computing
Approximate recognition of non-regular languages by finite automata
ACSC '05 Proceedings of the Twenty-eighth Australasian conference on Computer Science - Volume 38
Elements of Information Theory (Wiley Series in Telecommunications and Signal Processing)
Elements of Information Theory (Wiley Series in Telecommunications and Signal Processing)
Data streams: algorithms and applications
Foundations and Trends® in Theoretical Computer Science
On the existence of regular approximations
Theoretical Computer Science
Robust lower bounds for communication and stream computation
STOC '08 Proceedings of the fortieth annual ACM symposium on Theory of computing
Stream Order and Order Statistics: Quantile Estimation in Random-Order Streams
SIAM Journal on Computing
Estimating a binomial parameter with finite memory
IEEE Transactions on Information Theory
| Hi-index | 0.00 |
We investigate bounded-memory estimators of statistical functionals. It is shown that, for nondegenerate functionals and stochastic processes, it is impossible to achieve consistent estimation with bounded memory. In the positive direction, we show that O(log(1/驴)) states suffice to achieve 驴-consistent estimation for a natural class of functionals. A canonical optimal construction is conjectured for arbitrary statistical functionals.