Mean and Variance Estimation Complexity in Arbitrary Distributions via Wasserstein Minimization
Organizations: Department of Combinatorics & Optimization, University of Waterloo, Waterloo, Ontario, Canada N2L 3G1
Abstract
Parameter estimation is a fundamental challenge in machine learning, crucial for tasks such as neural network weight fitting and Bayesian inference. This paper focuses on the complexity of estimating translation and shrinkage parameters for a distribution of the form , where is a known density in given samples. We highlight that while the problem is NP-hard for Maximum Likelihood Estimation (MLE), it is possible to obtain -approximations for arbitrary within time using the Wasserstein distance.
Parameter Estimation
Parameter estimation studies how to infer unknown quantities in statistical, physical, and machine-learning models from observed data.
See all 156 papers