6 citations · 7 across the 4 of their papers we have counts for
6 papers · 1 filter
Entropic Independence II: Optimal Sampling and Concentration via Restricted Modified Log-Sobolev Inequalities
Nima Anari, Vishesh Jain, Frederic Koehler +2
We introduce a framework for obtaining tight mixing times for Markov chains based on what we call restricted modified log-Sobolev inequalities. Modified log-Sobolev inequalities (M…
Domain Sparsification of Discrete Distributions using Entropic Independence
Nima Anari, Michał Dereziński, Thuy-Duong Vuong +1
We present a framework for speeding up the time it takes to sample from discrete distributions defined over subsets of size of a ground set of elements, in the regime $…
Entropic Independence I: Modified Log-Sobolev Inequalities for Fractionally Log-Concave Distributions and High-Temperature Ising Models
Nima Anari, Vishesh Jain, Frederic Koehler +2
We introduce a notion called entropic independence that is an entropic analog of spectral notions of high-dimensional expansion. Informally, entropic independence of a background d…
Spectral independence, coupling with the stationary distribution, and the spectral gap of the Glauber dynamics
Vishesh Jain, Huy Tuan Pham, Thuy Duong Vuong
We present a new lower bound on the spectral gap of the Glauber dynamics for the Gibbs distribution of a spectrally independent -spin system on a graph with maximum…
On the sampling Lovász Local Lemma for atomic constraint satisfaction problems
Vishesh Jain, Huy Tuan Pham, Thuy-Duong Vuong
We study the problem of sampling an approximately uniformly random satisfying assignment for atomic constraint satisfaction problems i.e. where each constraint is violated by only…
Towards the sampling Lovász Local Lemma
Vishesh Jain, Huy Tuan Pham, Thuy Duong Vuong
Let be a constraint satisfaction problem on variables such that each constraint depends on at most variables and such that each variable…