15 citations · 22 across the 15 of their papers we have counts for
4 papers · 1 filter
No Free Lunch for Approximate MCMC
James E. Johndrow, Natesh S. Pillai, Aaron Smith
It is widely known that the performance of Markov chain Monte Carlo (MCMC) can degrade quickly when targeting computationally expensive posterior distributions, such as when the sa…
Universality and least singular values of random matrix products: a simplified approach
Rohit Chaudhuri, Vishesh Jain, Natesh S. Pillai
In this note, we show how to provide sharp control on the least singular value of a certain translated linearization matrix arising in the study of the local universality of produc…
Rate-optimal refinement strategies for local approximation MCMC
Andrew D. Davis, Youssef Marzouk, Aaron Smith +1
Many Bayesian inference problems involve target distributions whose density functions are computationally expensive to evaluate. Replacing the target density with a local approxima…
Fast and memory-optimal dimension reduction using Kac's walk
Vishesh Jain, Natesh S. Pillai, Ashwin Sah +2
In this work, we analyze dimension reduction algorithms based on the Kac walk and discrete variants. (1) For points in , we design an optimal Johnson-Lindenstra…