Context Tree Switching

@article{Veness2012ContextTS,
  title={Context Tree Switching},
  author={J. Veness and K. S. Ng and Marcus Hutter and Michael Bowling},
  journal={2012 Data Compression Conference},
  year={2012},
  pages={327-336}
}
  • J. Veness, K. S. Ng, +1 author Michael Bowling
  • Published 2012
  • Computer Science, Mathematics
  • 2012 Data Compression Conference
  • This paper describes the Context Tree Switching technique, a modification of Context Tree Weighting for the prediction of binary, stationary, n-Markov sources. By modifying Context Tree Weighting's recursive weighting scheme, it is possible to mix over a strictly larger class of models without increasing the asymptotic time or space complexity of the original algorithm. We prove that this generalization preserves the desirable theoretical properties of Context Tree Weighting on stationary n… CONTINUE READING
    42 Citations

    Figures, Tables, and Topics from this paper.

    Skip Context Tree Switching
    • 32
    • PDF
    Partition Tree Weighting
    • 15
    • PDF
    Generalized Probability Smoothing
    Cover tree Bayesian reinforcement learning
    • 16
    • PDF
    Count-Based Frequency Estimation with Bounded Memory
    • 3
    • PDF
    On Probability Estimation by Exponential Smoothing
    • C. Mattern
    • Computer Science, Mathematics
    • 2015 Data Compression Conference
    • 2015
    • 3
    • PDF
    Generalized Context Modeling With Multi-Directional Structuring and MDL-Based Model Selection for Heterogeneous Data Compression
    • 2
    • PDF
    Dynamic-Depth Context Tree Weighting
    • 2
    • PDF
    On Probability Estimation via Relative Frequencies and Discount
    • C. Mattern
    • Mathematics, Computer Science
    • 2015 Data Compression Conference
    • 2015
    • 2
    • PDF

    References

    SHOWING 1-10 OF 21 REFERENCES
    The context-tree weighting method : basic properties
    • J FransM.
    • 2004
    • 267
    • PDF
    The context-tree weighting method: basic properties
    • 667
    • PDF
    Reflections on “ The Context-Tree Weighting Method : Basic Properties ”
    • F. Willems, Yuri Shtarkovy, Tjalling Tjalkensz
    • 2002
    • 14
    • PDF
    On Prediction Using Variable Order Markov Models
    • 382
    • PDF
    Catching Up Faster in Bayesian Model Selection and Model Averaging
    • 46
    • PDF
    Complexity reduction of the context-tree weighting algorithm : a study for KPN Research
    • 23
    • PDF
    Switching between two universal source coding algorithms
    • 70
    • Highly Influential
    Data Compression Using Adaptive Coding and Partial String Matching
    • 1,222
    • PDF
    Lossless Compression Based on the Sequence Memoizer
    • 34
    • PDF
    Tracking the Best Expert
    • 288
    • PDF