Jonathan Niles-Weed

activity

20172026

most citedSharp Convergence Rates for Empirical Optimal Transport with Smooth Costs

25 citations · 53 across the 10 of their papers we have counts for

collaborators

Showing 2019Show all

3 papers · 1 filter

math.ST2019★ 9 cited

Estimation of Wasserstein distances in the Spiked Transport Model

Jonathan Niles-Weed, Philippe Rigollet

We propose a new statistical model, the spiked transport model, which formalizes the assumption that two probability distributions differ only on a low-dimensional subspace. We stu…

math.ST2019

Convergence of Smoothed Empirical Measures with Applications to Entropy Estimation

Ziv Goldfeld, Kristjan Greenewald, Yury Polyanskiy +1

This paper studies convergence of empirical measures smoothed by a Gaussian kernel. Specifically, consider approximating $P * N_{σ}$ , for $\mathcal{N}_σ\triangleq\mathcal{…

math.ST2019

Minimax estimation of smooth densities in Wasserstein distance

Jonathan Niles-Weed, Quentin Berthet

We study nonparametric density estimation problems where error is measured in the Wasserstein distance, a metric on probability distributions popular in many areas of statistics an…