2016
NeurIPS
NeurIPS 2016
On Mixtures of Markov Chains
Abstract
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.
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Data Science & Analytics and Mathematics & Optimization
🐣
Hot Topic Early Bird
- spectral method
Authors
Topics
Machine Learning > Core Methods > Clustering
Machine Learning > Optimization & Theory > Stochastic Processes
Data Science & Analytics > Methods > Time Series Analysis
Machine Learning > Bayesian & Probabilistic > Probabilistic Modeling
Machine Learning > Core Methods > Graphical Models
Mathematics & Optimization > Statistics
Mathematics & Optimization > Probability > Stochastic Processes