Corpus ID: 5017575

Clustering Time Series and the Surprising Robustness of HMMs

@article{Kozdoba2016ClusteringTS,
  title={Clustering Time Series and the Surprising Robustness of HMMs},
  author={Mark Kozdoba and Shie Mannor},
  journal={ArXiv},
  year={2016},
  volume={abs/1605.02531}
}
  • Mark Kozdoba, Shie Mannor
  • Published 2016
  • Computer Science, Mathematics
  • ArXiv
  • Suppose that we are given a time series where consecutive samples are believed to come from a probabilistic source, that the source changes from time to time and that the total number of sources is fixed. Our objective is to estimate the distributions of the sources. A standard approach to this problem is to model the data as a hidden Markov model (HMM). However, since the data often lacks the Markov or the stationarity properties of an HMM, one can ask whether this approach is still suitable… CONTINUE READING
    Clustering Time-Series by a Novel Slope-Based Similarity Measure Considering Particle Swarm Optimization
    1

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 42 REFERENCES
    Hidden semi-Markov models
    513
    Asymptotical statistics of misspecified hidden Markov models
    30
    A Method of Moments for Mixture Models and Hidden Markov Models
    263
    Exponential Forgetting and Geometric Ergodicity in Hidden Markov Models
    149
    Learning Topic Models -- Going beyond SVD
    314