On Mixtures of Markov Chains

被引：0
|
作者：
Gupta, Rishi [1 ,2 ]
Kumar, Ravi [2 ]
Vassilvitskii, Sergei [3 ]
机构：
[1] Stanford Univ, Stanford, CA 94305 USA
[2] Google Res, Mountain View, CA USA
[3] Google Res, New York, NY 10011 USA
来源：
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016) | 2016年 / 29卷
关键词：
MAXIMUM-LIKELIHOOD;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We study the problem of reconstructing a mixture of Markov chains from the trajectories generated by random walks through the state space. Under mild non-degeneracy conditions, we show that we can uniquely reconstruct the underlying chains by only considering trajectories of length three, which represent triples of states. Our algorithm is spectral in nature, and is easy to implement.
引用
收藏
页数：9
相关论文
共 50 条
  • [1] On mixtures of distributions of Markov chains
    Fortini, S
    Ladelli, L
    Petris, G
    Regazzini, E
    [J]. STOCHASTIC PROCESSES AND THEIR APPLICATIONS, 2002, 100 : 147 - 165
  • [2] Inferring mixtures of Markov chains
    Batu, T
    Guha, S
    Kannan, S
    [J]. LEARNING THEORY, PROCEEDINGS, 2004, 3120 : 186 - 199
  • [3] Infinite Mixtures of Markov Chains
    Reubold, Jan
    Boubekki, Ahcene
    Strufe, Thorsten
    Brefeld, Ulf
    [J]. NEW FRONTIERS IN MINING COMPLEX PATTERNS, NFMCP 2017, 2018, 10785 : 167 - 181
  • [4] Predictive characterization of mixtures of Markov chains
    Fortini, Sandra
    Petrone, Sonia
    [J]. BERNOULLI, 2017, 23 (03) : 1538 - 1565
  • [5] TRACE INEQUALITIES FOR MIXTURES OF MARKOV-CHAINS
    SINGER, B
    SPILERMAN, S
    [J]. ADVANCES IN APPLIED PROBABILITY, 1977, 9 (04) : 747 - 764
  • [6] Mixtures of adaptive controllers based on Markov chains: A future of intelligent control?
    Karny, M
    Valeckova, M
    Gao, H
    [J]. UKACC INTERNATIONAL CONFERENCE ON CONTROL '98, VOLS I&II, 1998, : 721 - 726
  • [7] Simplicial mixtures of Markov chains:: Distributed modelling of dynamic user profiles
    Girolami, M
    Kabán, A
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 16, 2004, 16 : 9 - 16
  • [8] Learning Mixtures of Markov Chains from Aggregate Data with Structural Constraints
    Luo, Dixin
    Xu, Hongteng
    Zhen, Yi
    Dilkina, Bistra
    Zha, Hongyuan
    Yang, Xiaokang
    Zhang, Wenjun
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2016, 28 (06) : 1518 - 1531
  • [9] Markov models—Markov chains
    Jasleen K. Grewal
    Martin Krzywinski
    Naomi Altman
    [J]. Nature Methods, 2019, 16 : 663 - 664
  • [10] Time-Varying Mixtures of Markov Chains: An Application to Road Traffic Modeling
    Lawlor, Sean
    Rabbat, Michael G.
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2017, 65 (12) : 3152 - 3167
12345