Switching between two universal source coding algorithms
P.A.J. Volf, F.M.J. Willems · DCC · 2002
This paper discusses a switching method which can be used to combine two sequential universal source coding algorithms. The switching method treats these two algorithms as black-boxes and can only use their estimates of the probability distributions for the consecutive symbols of the source sequence. Three weighting algorithms based on this switching method are presented. Empirical results show that all three weighting algorithms give a performance better than the performance of the source coding algorithms they combine.
Cited by 59 works. doi:10.1109/dcc.1998.672217
Authors
References
- The context-tree weighting method: basic properties
- A note on the Ziv - Lempel model for compressing individual sequences (Corresp.)
- The design and analysis of efficient lossless data compression systems
- Coding for a binary independent piecewise-identically-distributed source
- A percolating state selector for suffix-tree context models