Limit laws for the height in PATRICIA tries
Journal of Algorithms - Analysis of algorithms
Analyzing a class of pseudo-random bit generator through inductive machine learning paradigm
Intelligent Data Analysis
Universal reinforcement learning
IEEE Transactions on Information Theory
Time series forecasting of web performance data monitored by MWING multiagent distributed system
ICCCI'10 Proceedings of the Second international conference on Computational collective intelligence: technologies and applications - Volume PartI
On families of new adaptive compression algorithms suitable for time-varying source data
ADVIS'04 Proceedings of the Third international conference on Advances in Information Systems
A fast and efficient nearly-optimal adaptive Fano coding scheme
Information Sciences: an International Journal
Collective suffix tree-based models for location prediction
Proceedings of the 2013 ACM conference on Pervasive and ubiquitous computing adjunct publication
| Hi-index | 754.90 |
We consider a universal predictor based on pattern matching. Given a sequence X1, ..., Xn drawn from a stationary mixing source, it predicts the next symbol Xn+1 based on selecting a context of Xn+1. The predictor, called the sampled pattern matching (SPM), is a modification of the Ehrenfeucht-Mycielski (1992) pseudorandom generator algorithm. It predicts the value of the most frequent symbol appearing at the so-called sampled positions. These positions follow the occurrences of a fraction of the longest suffix of the original sequence that has another copy inside X1X2···Xn ; that is, in SPM, the context selection consists of taking certain fraction of the longest match. The study of the longest match for lossless data compression was initiated by Wyner and Ziv in their 1989 seminal paper. Here, we estimate the redundancy of the SPM universal predictor, that is, we prove that the probability the SPM predictor makes worse decisions than the optimal predictor is O(n-ν) for some 0<ν<½ as n→∞. As a matter of fact, we show that we can predict K=O(1) symbols with the same probability of error