Pith. sign in

Memory Efficient And Minimax Distribution Estimation Under Wasserstein Distance Using Bayesian Histograms

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

We study Bayesian histograms for distribution estimation on $[0,1]^d$ under the Wasserstein $W_v, 1 \leq v < \infty$ distance in the i.i.d sampling regime. We newly show that when $d < 2v$, histograms possess a special \textit{memory efficiency} property, whereby in reference to the sample size $n$, order $n^{d/2v}$ bins are needed to obtain minimax rate optimality. This result holds for the posterior mean histogram and with respect to posterior contraction: under the class of Borel probability measures and some classes of smooth densities. The attained memory footprint overcomes existing minimax optimal procedures by a polynomial factor in $n$; for example an $n^{1 - d/2v}$ factor reduction in the footprint when compared to the empirical measure, a minimax estimator in the Borel probability measure class. Additionally constructing both the posterior mean histogram and the posterior itself can be done super--linearly in $n$. Due to the popularity of the $W_1,W_2$ metrics and the coverage provided by the $d < 2v$ case, our results are of most practical interest in the $(d=1,v =1,2), (d=2,v=2), (d=3,v=2)$ settings and we provide simulations demonstrating the theory in several of these instances.

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Stochastic Weight Sharing for Bayesian Neural Networks

cs.LG · 2025-05-23 · conditional · novelty 6.0

2DGBNN compresses Bayesian neural networks by clustering weight means and variances into shared 2D Gaussians, reducing parameter counts by up to 99% on ImageNet-scale models with small accuracy losses.

citing papers explorer

Showing 1 of 1 citing paper.

  • Stochastic Weight Sharing for Bayesian Neural Networks cs.LG · 2025-05-23 · conditional · none · ref 27 · internal anchor

    2DGBNN compresses Bayesian neural networks by clustering weight means and variances into shared 2D Gaussians, reducing parameter counts by up to 99% on ImageNet-scale models with small accuracy losses.