ICML 2025poster1 citations
A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation
Jongha Jon Ryu, Abhin Shah, Gregory W. Wornell
Abstract
This paper studies a family of estimators based on noise-contrastive estimation (NCE) for learning unnormalized distributions. The main contribution of this work is to provide a unified perspective on various methods for learning unnormalized distributions, which have been independently proposed and studied in separate research communities, through the lens of NCE. This unified view offers new insights into existing estimators. Specifically, for exponential families, we establish the finite-sample convergence rates of the proposed estimators under a set of regularity assumptions, most of which are new.
unnormalized modelsexponential family distributionsnoise-contrastive estimationinteractive screeningfinite-sample analysis
BibTeX
@inproceedings{
ryu2025a,
title={A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation},
author={Jongha Jon Ryu and Abhin Shah and Gregory W. Wornell},
booktitle={Forty-second International Conference on Machine Learning},
year={2025},
url={https://openreview.net/forum?id=Wwj6jjxZet}
}