5 citations · 17 across the 11 of their papers we have counts for
7 papers · 1 filter
Optimistic Estimation of Convergence in Markov Chains with the Average-Mixing Time
Geoffrey Wolfer, Pierre Alquier
The convergence rate of a Markov chain to its stationary distribution is typically assessed using the concept of total variation mixing time. However, this worst-case measure often…
Variance-Aware Estimation of Kernel Mean Embedding
Geoffrey Wolfer, Pierre Alquier
An important feature of kernel mean embeddings (KME) is that the rate of convergence of the empirical KME to the true distribution KME can be bounded independently of the dimension…
Improved Estimation of Relaxation Time in Non-reversible Markov Chains
Geoffrey Wolfer, Aryeh Kontorovich
We show that the minimax sample complexity for estimating the pseudo-spectral gap of an ergodic Markov chain in constant multiplicative error is of the order of $…
Identity testing of reversible Markov chains
Sela Fried, Geoffrey Wolfer
We consider the problem of identity testing of Markov chain transition matrices based on a single trajectory of observations under the distance notion introduced by Daskalakis et a…
Learning discrete distributions with infinite support
Doron Cohen, Aryeh Kontorovich, Geoffrey Wolfer
We present a novel approach to estimating discrete distributions with (potentially) infinite support in the total variation metric. In a departure from the established paradigm, we…
Estimating the Mixing Time of Ergodic Markov Chains
Geoffrey Wolfer, Aryeh Kontorovich
We address the problem of estimating the mixing time of an arbitrary ergodic finite-state Markov chain from a single trajectory of length . The reversible cas…
Mixing time estimation in reversible Markov chains from a single sample path
Daniel Hsu, Aryeh Kontorovich, David A. Levin +2
The spectral gap of a finite, ergodic, and reversible Markov chain is an important parameter measuring the asymptotic rate of convergence. In applications, the transition matri…