The DOI matches its Crossref record.
Testing that distributions are close
Abstract
Given two distributions over an n element set, we wish to check whether these distributions are statistically close by only sampling. We give a sublinear algorithm which uses O(n/sup 2/3//spl epsiv//sup -4/ log n) independent samples from each distribution, runs in time linear in the sample size, makes no assumptions about the structure of the distributions, and distinguishes the cases when the distance between the distributions is small (less than max(/spl epsiv//sup 2//32/sup 3//spl radic/n,/spl epsiv//4/spl radic/n=)) or large (more than /spl epsiv/) in L/sub 1/-distance. We also give an /spl Omega/(n/sup 2/3//spl epsiv//sup -2/3/) lower bound. Our algorithm has applications to the problem of checking whether a given Markov process is rapidly mixing. We develop sublinear algorithms for this problem as well.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cited by
A theory of learning from different domains
Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., & Vaughan, J. W. (2010) · Machine Learning · doi:10.1007/s10994-009-5152-4 · Cited by 3,515
“First, it cannot be accurately estimated from finite samples of arbitrary distributions (Batu et al. 2000; Kifer et al. 2004) and therefore has limited usefulness in practice.”
BackgroundAnalysis of Representations for Domain Adaptation
Ben-David, S., Blitzer, J., Crammer, K., & Pereira, F. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0022 · Cited by 2,019
“Unfortunately the variational distance between real-valued distributions cannot be computed from finite samples [2, 9] and therefore is not useful to us when investigating representations for domain adaptation on real-world data.”
BackgroundDataset Shift in Machine Learning
(2008) · doi:10.7551/mitpress/9780262170055.001.0001 · Cited by 1,553
Equilibration, thermalisation, and the emergence of statistical mechanics in closed quantum systems
Gogolin, C., & Eisert, J. (2016) · Reports on Progress in Physics · doi:10.1088/0034-4885/79/5/056001 · Cited by 999
Detecting Change in Data Streams
Kifer, D., Ben-David, S., & Gehrke, J. (2004) · Proceedings 2004 VLDB Conference · doi:10.1016/b978-012088469-8.50019-x · Cited by 789
The Specious Art of Single-Cell Genomics
Chari, T., & Pachter, L. (2021) · doi:10.1101/2021.08.25.457696 · Cited by 379
“We also present results with the L1 norm (shown in Supplementary Materials), as L1 is more suitable for measuring distance in high dimensions, particularly in comparison to other L norms [29, 30], and is commonly applied to transcriptomic data [31–33], with comparable performance to the probabilistic Jensen-Shannon di…”
MethodIntroduction to Property Testing
Goldreich, O. (2017) · Cambridge University Press eBooks · doi:10.1017/9781108135252 · Cited by 270
Metadata
- Authors
- Batu, T., Fortnow, L., Rubinfeld, R., Smith, W. D., & White, P.
- Venue
- Proceedings 41st Annual Symposium on Foundations of Computer Science
- Publisher
- IEEE Comput. Soc
- Published
- 2002-11-07
- Pages
- 259-269
- ISSN
- 0272-5428 (ISSN-L)
- OpenAlex
- W2134169350
- Cited by
- 247
- References
- 0
- FWCI
- 3.45
- Type
- conference paper
- Language
- en
- Open access
- closed
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.