PlumX Metrics
Embed PlumX Metrics

SHARP CONVERGENCE RATES FOR EMPIRICAL OPTIMAL TRANSPORT WITH SMOOTH COSTS

Annals of Applied Probability, ISSN: 1050-5164, Vol: 34, Issue: 1 B, Page: 1108-1135
2024
  • 6
    Citations
  • 0
    Usage
  • 5
    Captures
  • 1
    Mentions
  • 0
    Social Media
Metric Options:   Counts1 Year3 Year

Metrics Details

  • Citations
    6
  • Captures
    5
  • Mentions
    1
    • News Mentions
      1
      • 1

Most Recent News

Studies from Carnegie Mellon University Have Provided New Information about Applied Probability (Sharp Convergence Rates for Empirical Optimal Transport With Smooth Costs)

2024 APR 09 (NewsRx) -- By a News Reporter-Staff News Editor at Math Daily News -- A new study on Mathematics - Applied Probability is

Article Description

We revisit the question of characterizing the convergence rate of plug-in estimators of optimal transport costs. It is well known that an empirical measure comprising independent samples from an absolutely continuous distribution on R converges to that distribution at the rate n in Wasserstein distance, which can be used to prove that plug-in estimators of many optimal transport costs converge at this same rate. However, we show that when the cost is smooth, this analysis is loose: plug-in estimators based on empirical measures converge quadratically faster, at the rate n. As a corollary, we show that the Wasserstein distance between two distributions is significantly easier to estimate when the measures are well-separated. We also prove lower bounds, showing not only that our analysis of the plug-in estimator is tight, but also that no other estimator can enjoy significantly faster rates of convergence uniformly over all pairs of measures. Our proofs rely on empirical process theory arguments based on tight control of L covering numbers for locally Lipschitz and semiconcave functions. As a byproduct of our proofs, we derive L estimates on the displacement induced by the optimal coupling between any two measures satisfying suitable concentration and anticoncentration conditions, for a wide range of cost functions.

Provide Feedback

Have ideas for a new metric? Would you like to see something else here?Let us know