We study the worst-case communication complexity of distributed algorithms computing a path problem based on stationary distributions of random walks in a network G with the caveat...
We consider a class of Markov chains known for its closed form transient and steady-state distributions. We show that some absorbing chains can be also seen as members of this clas...
We show how to bound the mixing time and log-Sobolev constants of Markov chains by bounding the edge-isoperimetry of their underlying graphs. To do this we use two recent techniqu...
In this paper we consider the problem of policy evaluation in reinforcement learning, i.e., learning the value function of a fixed policy, using the least-squares temporal-differe...
Alessandro Lazaric, Mohammad Ghavamzadeh, Ré...
In this paper, we develop a new "robust mixing" framework for reasoning about adversarially modified Markov Chains (AMMC). Let P be the transition matrix of an irreducib...