Year: 2025
Type: preprint
Abstract: A distribution over instances of a sampling problem is said to exhibit transport disorder chaos if perturbing the instance by a small amount of random noise dramatically changes the stationary distribution (in Wasserstein distance). Seeking to provide evidence that some sampling tasks are hard on average, a recent line of work has demonstrated that disorder chaos is sufficient to rule out "stable" sampling algorithms, such as gradient methods and some diffusion processes. We demonstrate that disorder chaos does not preclude polynomial-time sampling by canonical algorithms in canonical models. We show that with high probability over a random graph $\boldsymbol{G} \sim G(n,1/2)$: (1) the hardcore model (at fugacity $λ= 1$) on $\boldsymbol{G}$ exhibits disorder chaos, and (2) Glauber dynamics run for $O(n)$ time can approximately sample from the hardcore model on $\boldsymbol{G}$ (in Wasserstein distance).
Source: arXiv (Cornell University)
Authors: Ma, Eric, Schramm, Tselil
Language: English
Subfield: Statistics and Probability
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6967046031
Cites:
Cited by:
Related to: