On Mixtures of Markov Chains
Rishi Gupta ⋅ Ravi Kumar ⋅ Sergei Vassilvitskii
Keywords:
(Other) Unsupervised Learning Methods
2016 Poster
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.
Chat is not available.
Successful Page Load