Learning Probability Measures with respect to Optimal Transport Metrics
arXiv:1209.1077
Abstract
We study the problem of estimating, in the sense of optimal transport metrics, a measure which is assumed supported on a manifold embedded in a Hilbert space. By establishing a precise connection between optimal transport metrics, optimal quantization, and learning theory, we derive new probabilistic bounds for the performance of a classic algorithm in unsupervised learning (k-means), when used to produce a probability measure derived from the data. In the course of the analysis, we arrive at new lower bounds, as well as probabilistic upper bounds on the convergence rate of the empirical law of large numbers, which, unlike existing bounds, are applicable to a wide class of measures.
13 pages, 2 figures. Advances in Neural Information Processing Systems, NIPS 2012
Cited by in corpus (21)
- Statistical Aspects of Wasserstein Distances
- Fast Computation of Wasserstein Barycenters
- Understanding GANs: the LQG Setting
- Robust Hypothesis Testing Using Wasserstein Uncertainty Sets
- A Flexible Framework for Multi-Objective Bayesian Optimization using Random Scalarizations
- How Well Generative Adversarial Networks Learn Distributions
- Minimax Distribution Estimation in Wasserstein Distance
- Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning
- Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)
- Quantitative stability of optimal transport maps and linearization of the 2-Wasserstein space
- Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time
- (q,p)-Wasserstein GANs: Comparing Ground Metrics for Wasserstein GANs
- Projection Robust Wasserstein Distance and Riemannian Optimization
- Model Imitation for Model-Based Reinforcement Learning
- Wasserstein Measure Coresets
- Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation
- Distributionally Robust XVA via Wasserstein Distance: Wrong Way Counterparty Credit and Funding Risk
- Improving Approximate Optimal Transport Distances using Quantization
- Nearly Tight Convergence Bounds for Semi-discrete Entropic Optimal Transport
- On the asymptotics of Ajtai-Komlós-Tusnády statistics
- Permutation invariant networks to learn Wasserstein metrics