Journal article · 2026 · Open access
Minimax Rates for the Estimation of Eigenpairs of Weighted Laplace–Beltrami Operators on Manifolds
IEEE Transactions on Information Theory, 72(11), 8778–8815 · Published 27 August 2026 · DOI 10.1109/tit.2026.3727845
In brief
“Minimax Rates for the Estimation of Eigenpairs of Weighted Laplace–Beltrami Operators on Manifolds” is a 2026 journal article by Nicolás García Trillos and 2 co-authors, published in IEEE Transactions on Information Theory. OpenAlex counts 15 citations as of 17 November 2026, which puts it in the top 3% of works published in 2026 by citations. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 15
- Most cited in
- 2026 (10)
- Field-weighted impact
- 12.57
- References
- 61
- Authors
- 3
Abstract
We study the problem of estimating eigenpairs of elliptic differential operators from samples of a distribution $ρ$ supported on a manifold $M$. The operators discussed in the paper are relevant in unsupervised learning and in particular are obtained by taking suitable scaling limits of widely used graph Laplacians over data clouds. We study the minimax risk for this eigenpair estimation problem and explore the rates of approximation that can be achieved by commonly used graph Laplacians built from random data. More concretely, assuming that $ρ$ belongs to a certain family of distributions with controlled second derivatives, and assuming that the $d$-dimensional manifold $M$ where $ρ$ is supported has bounded geometry, we prove that the statistical minimax rate for approximating eigenvalues and eigenvectors in the $H^1(M)$-sense is $n^{-2/(d+4)}$, a rate that matches the minimax rate for a closely related density estimation problem. We then revisit the literature studying Laplacians over proximity graphs in the large data limit and prove that, under slightly stronger regularity assumptions on the data generating model, eigenpairs of graph Laplacians induce manifold agnostic estimators with an error of approximation that, up to logarithmic corrections, matches our lower bounds. Our analysis allows us to expand the existing literature on graph-based learning in at least two significant ways: 1) we consider stronger norms to measure the error of approximation than the ones that had been analyzed in the past; 2) our rates of convergence are uniform over a family of smooth distributions and do not just apply to densities with special symmetries, and, as a consequence of our lower bounds, are essentially sharp when the connectivity of the graph is sufficiently high.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Trillos, N. G., Cheng-hui, L., & Venkatraman, R. (2026). Minimax Rates for the Estimation of Eigenpairs of Weighted Laplace–Beltrami Operators on Manifolds. IEEE Transactions on Information Theory, 72(11), 8778–8815. https://doi.org/10.1109/tit.2026.3727845
MLA 9
Trillos, Nicolás García, et al. “Minimax Rates for the Estimation of Eigenpairs of Weighted Laplace–Beltrami Operators on Manifolds.” IEEE Transactions on Information Theory, vol. 72, no. 11, 2026, pp. 8778–8815. https://doi.org/10.1109/tit.2026.3727845.
Chicago
Trillos, Nicolás García, LI Cheng-hui, and Raghavendra Venkatraman. 2026. “Minimax Rates for the Estimation of Eigenpairs of Weighted Laplace–Beltrami Operators on Manifolds.” IEEE Transactions on Information Theory 72 (11): 8778–8815. https://doi.org/10.1109/tit.2026.3727845.
Harvard
Trillos, N. G., Cheng-hui, L. and Venkatraman, R. (2026) ‘Minimax Rates for the Estimation of Eigenpairs of Weighted Laplace–Beltrami Operators on Manifolds’, IEEE Transactions on Information Theory, 72(11), pp. 8778–8815. doi:10.1109/tit.2026.3727845.
IEEE
N. G. Trillos, L. Cheng-hui, and R. Venkatraman, “Minimax Rates for the Estimation of Eigenpairs of Weighted Laplace–Beltrami Operators on Manifolds,” IEEE Transactions on Information Theory, vol. 72, no. 11, pp. 8778–8815, 2026, doi: 10.1109/tit.2026.3727845.
BibTeX
@article{trillos2026minimax,
title = {{Minimax Rates for the Estimation of Eigenpairs of Weighted Laplace–Beltrami Operators on Manifolds}},
author = {Trillos, Nicolás García and Cheng-hui, LI and Venkatraman, Raghavendra},
journal = {IEEE Transactions on Information Theory},
year = {2026},
volume = {72},
number = {11},
pages = {8778--8815},
doi = {10.1109/tit.2026.3727845},
url = {https://doi.org/10.1109/tit.2026.3727845}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- minimax rates
- graph Laplacian
- manifold learning
- unsupervised learning
- proximity graphs
- density estimation
- eigenvalue approximation
- eigenvector approximation
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Trillos, N. G., Cheng-hui, L., & Venkatraman, R. (2026). Minimax Rates for the Estimation of Eigenpairs of Weighted Laplace–Beltrami Operators on Manifolds. IEEE Transactions on Information Theory, 72(11), 8778–8815. https://doi.org/10.1109/tit.2026.3727845
How many times has this paper been cited?
15 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 arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Nicolás García Trillos, LI Cheng-hui, Raghavendra Venkatraman.
What is the DOI of this paper?
10.1109/tit.2026.3727845, permanently at https://doi.org/10.1109/tit.2026.3727845. 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.