5 papers
True Self-Avoiding Walk for Accelerating Markov-Chain Monte Carlo Integration
Qinghua, Ding, Venkat Anantharam
We study true self-avoiding walk (TSAW) as a mechanism for improving empirical integral estimation via Markov chain Monte Carlo (MCMC). We consider finite-state adaptive sampling d…
An Information-theoretic Analysis of Edge-reinforced Random Walks
Qinghua, Ding, Venkat Anantharam
Reinforced random walks are random walks on graphs whose transition probabilities along edges from a vertex are proportional to the weights of those edges, but where the weight of…
The Density Formula Approach for Non-reversible Isomorphism Theorems, with Applications
Qinghua, Ding, Venkat Anantharam
The classical isomorphism theorems for reversible Markov chains have played an important role in studying the properties of local time processes of strongly symmetric Markov proces…
On Statistical Estimation of Edge-Reinforced Random Walks
Qinghua, Ding, Venkat Anantharam
Reinforced random walks (RRWs), including vertex-reinforced random walks (VRRWs) and edge-reinforced random walks (ERRWs), model random walks where the transition probabilities evo…
Quantum advantage in decentralized control of POMDPs: A control-theoretic view of the Mermin-Peres square
Venkat Anantharam
Consider a decentralized partially-observed Markov decision problem (POMDP) with multiple cooperative agents aiming to maximize a long-term-average reward criterion. We observe tha…