A Unified View on Learning Unnormalized Distributions via Noise-Contrastive Estimation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 18 of its 36 references that are in the map. First posted on arXiv 26 Sep 2024.
Builds on
18 of 36 references.
References · 18
- 2019Sliced Score Matching: A Scalable Approach to Density and Score Estimationcited by 381
- 2021How to Train Your Energy-Based Modelscited by 271
- 2016Interaction Screening: Efficient and Sample-Optimal Learning of Ising Modelscited by 43
- 2018Conditional Noise-Contrastive Estimation of Unnormalised Modelscited by 25
- 2019Efficient Learning of Discrete Graphical Modelscited by 21
- 2019Estimating Density Models with Truncation Boundaries using Score Matchingcited by 20
- 2023Provable benefits of score matchingcited by 18
- 2021Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimationcited by 15
- 2023Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyondcited by 13
- 2022The Optimal Noise in Noise-Contrastive Learning Is Not What You Thinkcited by 11
- 2021A Computationally Efficient Method for Learning Exponential Family Distributionscited by 10
- 2020On Learning Continuous Pairwise Markov Random Fieldscited by 9
6 more
- 2018Analysis of Noise Contrastive Estimation from the Perspective of Asymptotic Variancecited by 6
- 2021Learning Continuous Exponential Families Beyond Gaussiancited by 6
- 2022Pitfalls of Gaussians as a noise distribution in NCEcited by 6
- 2023Learning Unnormalized Statistical Models via Compositional Optimizationcited by 5
- 2023On Computationally Efficient Learning of Exponential Family Distributionscited by 2
- 2014The Poisson transform for unnormalised statistical modelscited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.