Minimax Posterior Contraction Rates for Unconstrained Distribution Estimation on $[0,1]^d$ Under Wasserstein Distance

Abstract

We obtain asymptotic minimax optimal posterior contraction rates for estimation of probability distributions on $[0,1]^d$ under the Wasserstein-$p$ metrics using Bayesian Histograms. To the best of our knowledge, our analysis is the first to provide minimax posterior contraction rates for every $p \geq 1$ and problem dimension $d \geq 1$. Our proof technique takes advantage of the conjugacy of the Bayesian Histogram.

Cite

Text

Jacobs et al. "Minimax Posterior Contraction Rates for Unconstrained Distribution Estimation on $[0,1]^d$ Under Wasserstein Distance." Transactions on Machine Learning Research, 2025.

Markdown

[Jacobs et al. "Minimax Posterior Contraction Rates for Unconstrained Distribution Estimation on $[0,1]^d$ Under Wasserstein Distance." Transactions on Machine Learning Research, 2025.](https://mlanthology.org/tmlr/2025/jacobs2025tmlr-minimax/)

BibTeX

@article{jacobs2025tmlr-minimax,
  title     = {{Minimax Posterior Contraction Rates for Unconstrained Distribution Estimation on $[0,1]^d$ Under Wasserstein Distance}},
  author    = {Jacobs, Peter Matthew and Patel, Lekha and Bhattacharya, Anirban and Pati, Debdeep},
  journal   = {Transactions on Machine Learning Research},
  year      = {2025},
  url       = {https://mlanthology.org/tmlr/2025/jacobs2025tmlr-minimax/}
}