University of Cambridge > Talks.cam > Statistics > Minimax estimation of smooth densities in Wasserstein distance

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Minimax estimation of smooth densities in Wasserstein distance

Download to your calendar using vCal

If you have a question about this talk, please contact Dr Sergio Bacallado .

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 and machine learning. We give the first minimax-optimal rates for this problem for general Wasserstein distances, and show that, unlike classical nonparametric density estimation, these rates depend on whether the densities in question are bounded below. Motivated by variational problems involving the Wasserstein distance, we also show how to construct discretely supported measures, suitable for computational purposes, which achieve the minimax rates. Our main technical tool is an inequality giving a nearly tight dual characterization of the Wasserstein distances in terms of Besov norms.

Joint work with Q. Berthet.

This talk is part of the Statistics series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Proteins, Genomes & Computers Faculty of Asian and Middle Eastern Studies (Sidgwick Site), Room 8-9 Nicky-minaj-net-worth

Other talks

Topology of the Ritz energy landscape Dwarf Galaxies in the Local Universe Shining a light on the origin of supermassive black holes with cosmological simulations Online Causal Inference Seminar Title to be confirmed Thelocactus
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity