The DOI matches its Crossref record; 23 of the 24 references it cites were found in a registry or an index.
Random Forests and Adaptive Nearest Neighbors
Abstract
In this article we study random forests through their connection with a new framework of adaptive nearest-neighbor methods. We introduce a concept of potential nearest neighbors (k-PNNs) and show that random forests can be viewed as adaptively weighted k-PNN methods. Various aspects of random forests can be studied from this perspective. We study the effect of terminal node sizes on the prediction accuracy of random forests. We further show that random forests with adaptive splitting schemes assign weights to k-PNNs in a desirable way: for the estimation at a given target point, these random forests assign voting weights to the k-PNNs of the target point according to the local importance of different input variables. We propose a new simple splitting scheme that achieves desirable adaptivity in a straightforward fashion. This simple scheme can be combined with existing algorithms. The resulting algorithm is computationally faster and gives comparable results. Other possible aspects of random forests, such as using linear combinations in splitting, are also discussed. Simulations and real datasets are used to illustrate the results.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“A critical step was subsequently taken by Lin and Jeon (2006), who highlighted an interesting connection between random forests and a particular class of nearest neighbor predictors, further developed by Biau and Devroye (2010).”
From A random forest guided tour (2016) · cites this paper as Lin and Jeon (2006)
In the citing paper
“This important connection was first pointed out by Lin and Jeon (2006), who proved that if X is uniformly distributed on [0 , 1] p then, provided tree growing is independent of Y 1 , . . . , Y n (such simplified models are sometimes called non-adaptive ), we have”
From A random forest guided tour (2016) · cites this paper as Lin and Jeon (2006)
In the citing paper
“Indeed, if exactly one point is left in the leaves and if there is no resampling, then no matter what splitting strategy is used, the forest estimate at x is a weighted average of the Y i whose corresponding X i are LNN of x .”
From A random forest guided tour (2016) · cites this paper as Lin and Jeon (2006)
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
Greedy function approximation: A gradient boosting machine
Friedman, J. H. (2001) · The Annals of Statistics · doi:10.1214/aos/1013203451 · Cited by 30,731
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
Breiman, L. (1996) · Machine Learning · doi:10.1007/bf00058655 · Cited by 16,325
Experiments with a new boosting algorithm
Freund, Y., & Schapire, R. E. (1996) · Cited by 8,189
Multivariate Adaptive Regression Splines
Friedman, J. H. (1991) · The Annals of Statistics · doi:10.1214/aos/1176347963 · Cited by 8,108
The random subspace method for constructing decision forests
Ho, T. K. (1998) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.709601 · Cited by 7,005
Friedman, J., Hastie, T., & Tibshirani, R. (2000) · The Annals of Statistics · doi:10.1214/aos/1016218223 · Cited by 6,884
Pattern Recognition and Neural Networks
Ripley, B. D. (1996) · Cambridge University Press eBooks · doi:10.1017/cbo9780511812651 · Cited by 6,500
The Strength of Weak Learnability
Schapire, R. E. (1990) · Machine Learning · doi:10.1007/bf00116037 · Cited by 4,600
Research works printed but not linked: 5
- Computation, 121, 256
- The Annals, Statistics, 19, 1
- Statistics, 28, 337
- Neighbor Classification, Pattern Recognition, 23, 1291
- The Annals, Statistics, 8, 1348
Cited by
Sorted by citations
Items 501–503 of 503
Hybrid machine learning: lasso and random forests
Zhang, G., & Pleis, J. R. (2026) · Journal of Applied Statistics · doi:10.1080/02664763.2026.2749636
Randomness In Tree Ensemble Methods
Elias, J. (2009) · The Mathematics Enthusiast
Risk Assessment and Pricing for Group Health Claims
Huang, S. (2015) · OpenCommons at University of Connecticut (University of Connecticut)
Metadata
- Authors
- Lin, Y., & Jeon, Y.
- Affiliations
- University of Wisconsin–Madison (US)
- ORCID
- Lin, Yi
- Venue
- Journal of the American Statistical Association
- Publisher
- Informa UK Limited
- Published
- 2006-06-01
- Volume
- 101
- Issue
- 474
- Pages
- 578-590
- ISSN
- 0162-1459 (ISSN-L)
- 1537-274X
- OpenAlex
- W2047081748
- Cited by
- 507
- References
- 24
- Citations by year
- 2026: 17 · 2025: 31 · 2024: 39 · 2023: 45 · 2022: 35 · 2021: 41 · 2020: 45 · 2019: 49 · 2018: 28 · 2017: 20 · 2016: 24 · 2015: 18 · 2014: 28 · 2013: 14 · 2012: 15
- FWCI
- 6.29
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of the American Statistical Association (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Inference
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Applications
- Keywords
- random forest, voting weights, feature importance, operator splitting, ensemble learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
