On rates of convergence in the Curie-Weiss-Potts model with external field
Peter Eichelsbacher, Bastian Martschink

TL;DR
This paper establishes convergence rates for the density vector in the Curie-Weiss-Potts model using Stein's Method, covering Gaussian and non-Gaussian limits across the entire parameter domain including critical points.
Contribution
It provides explicit convergence rates for the density vector in the Curie-Weiss-Potts model, including at critical points, using Stein's Method of exchangeable pairs.
Findings
Kolmogorov bounds for multivariate normal approximation
Convergence rates at the critical line and extremities
Explicit rates for non-Gaussian limits
Abstract
In the present paper we obtain rates of convergence for the limit theorems of the density vector in the Curie-Weiss-Potts model via Stein's Method of exchangeable pairs. Our results include Kolmogorov bounds for multivariate normal approximation in the whole domain and , where is the inverse temperature and an exterior field. In this model, the critical line is explicitly known and corresponds to a first order transition. We include rates of convergence for non-Gaussian approximations at the extremity of the critical line of the model.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
