Journal article · 2026 · Open access
Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias
Communications on Pure and Applied Mathematics, 79(6), 1467–1491 · Published 30 January 2026 · DOI 10.1002/cpa.70032
In brief
“Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias” is a 2026 journal article by Yifan Chen and 3 co-authors, published in Communications on Pure and Applied Mathematics. OpenAlex counts 11 citations as of 17 November 2026. It is open access: the full text is free to read at Communications on Pure and Applied Mathematics.
- Citations
- 11
- Most cited in
- 2026 (7)
- Field-weighted impact
- 9.87
- References
- 36
- Authors
- 4
Abstract
The unadjusted Langevin algorithm is commonly used to sample probability distributions in extremely high‐dimensional settings. However, existing analyses of the algorithm for strongly log‐concave distributions suggest that, as the dimension of the problem increases, the number of iterations required to ensure convergence within a desired error in the metric scales in proportion to or . In this paper, we argue that, despite this poor scaling of the error for the full set of variables, the behavior for a small number of variables can be significantly better: A number of iterations proportional to , up to logarithmic terms in , often suffices for the algorithm to converge to within a desired error for all ‐marginals. We refer to this effect as delocalization of bias . We show that the delocalization effect does not hold universally and prove its validity for Gaussian distributions and strongly log‐concave distributions with certain sparse interactions. Our analysis relies on a novel metric to measure convergence. A key technical challenge we address is the lack of a one‐step contraction property in this metric. Finally, we use asymptotic arguments to explore potential generalizations of the delocalization effect beyond the Gaussian and sparse interactions setting.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Chen, Y., Cheng, X., Weed, J., & Weare, J. (2026). Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias. Communications on Pure and Applied Mathematics, 79(6), 1467–1491. https://doi.org/10.1002/cpa.70032
MLA 9
Chen, Yifan, et al. “Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias.” Communications on Pure and Applied Mathematics, vol. 79, no. 6, 2026, pp. 1467–1491. https://doi.org/10.1002/cpa.70032.
Chicago
Chen, Yifan, Xiaoou Cheng, Jonathan Weed, and Jonathan Weare. 2026. “Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias.” Communications on Pure and Applied Mathematics 79 (6): 1467–1491. https://doi.org/10.1002/cpa.70032.
Harvard
Chen, Y. et al. (2026) ‘Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias’, Communications on Pure and Applied Mathematics, 79(6), pp. 1467–1491. doi:10.1002/cpa.70032.
IEEE
Y. Chen, X. Cheng, J. Weed, and J. Weare, “Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias,” Communications on Pure and Applied Mathematics, vol. 79, no. 6, pp. 1467–1491, 2026, doi: 10.1002/cpa.70032.
BibTeX
@article{chen2026convergence,
title = {{Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias}},
author = {Chen, Yifan and Cheng, Xiaoou and Weed, Jonathan and Weare, Jonathan},
journal = {Communications on Pure and Applied Mathematics},
year = {2026},
volume = {79},
number = {6},
pages = {1467--1491},
doi = {10.1002/cpa.70032},
url = {https://doi.org/10.1002/cpa.70032}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 3 | |
| 2025 | 1 | |
| 2026 | 7 |
Its field-weighted citation impact is 9.87: it has been cited 9.87 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Mathematics › Statistics and Probability › Markov Chains and Monte Carlo Methods
- unadjusted Langevin algorithm
- high-dimensional sampling
- convergence analysis
- normal distribution
- sparse interactions
- contraction metrics
- asymptotic analysis
- Markov chain Monte Carlo
Work with this paper
Most-cited papers in Mathematics
- Random ForestsLeo Breiman · Machine Learning · 2001 · 142,830 citations
- Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple TestingYoav Benjamini, Yosef Hochberg · Journal of the Royal Statistical Society Series B (Statistical Methodology) · 1995 · 113,923 citations
- Fitting Linear Mixed-Effects Models Using lme4Douglas M. Bates, Martin Maechler, Benjamin M. Bolker and 1 more · Journal of Statistical Software · 2015 · 100,328 citations
- The moderator-mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations.Reuben M. Baron, David A. Kenny · Journal of Personality and Social Psychology · 1986 · 95,866 citations
- Using multivariate statisticsBarbara Gerson Tabachnick, Linda S. Fidell · 1983 · 79,867 citations
Questions about this paper
How do I cite this paper in APA style?
Chen, Y., Cheng, X., Weed, J., & Weare, J. (2026). Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias. Communications on Pure and Applied Mathematics, 79(6), 1467–1491. https://doi.org/10.1002/cpa.70032
How many times has this paper been cited?
11 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Communications on Pure and Applied Mathematics: sign in and open the PDF from this page.
Who wrote this paper?
Yifan Chen, Xiaoou Cheng, Jonathan Weed, Jonathan Weare.
What is the DOI of this paper?
10.1002/cpa.70032, permanently at https://doi.org/10.1002/cpa.70032. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.