Minimax Estimation of Functionals of Discrete Distributions
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
We propose a general methodology for the construction and analysis of essentially minimax estimators for a wide class of functionals of finite dimensional parameters, and elaborate on the case of discrete distributions, where the support size S is unknown and may be comparable with or even much larger than the number of observations n. We treat the respective regions where the functional is nonsmooth and smooth separately. In the nonsmooth regime, we apply an unbiased estimator for the best polynomial approximation of the functional whereas, in the smooth regime, we apply a bias-corrected version of the maximum likelihood estimator (MLE). We illustrate the merit of this approach by thoroughly analyzing the performance of the resulting schemes for estimating two important information measures: 1) the entropy H(P) = ΣSi=1-piln piand 2) Fα(P) = ΣSi=1pαi, α > 0. We obtain the minimax L2rates for estimating these functionals. In particular, we demonstrate that our estimator achieves the optimal sample complexity n × S/ln S for entropy estimation. We also demonstrate that the sample complexity for estimating Fα(P), 01/α/ln S, which can be achieved by our estimator but not the MLE. For 12rate for estimating Fα(P) is (n ln n)-2(α-1)for infinite support size, while the maximum L2rate for the MLE is n-2(α-1). For all the above cases, the behavior of the minimax rate-optimal estimators with n samples is essentially that of the MLE (plug-in rule) with n ln n samples, which we term “effective sample size enlargement.” We highlight the practical advantages of our schemes for the estimation of entropy and mutual information. We compare our performance with various existing approaches, and demonstrate that our approach reduces running time and boosts the accuracy. Moreover, we show that the minimax rate-optimal mutual information estimator yielded by our framework leads to significant performance boosts over the Chow-Liu algorithm in learning graphical models. The wide use of information measure estimation suggests that the insights and estimators obtained in this paper could be broadly applicable.
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
Cites
Donoho, D. L. (2006) · IEEE Transactions on Information Theory · doi:10.1109/tit.2006.871582 · Cited by 23,994
Compression of individual sequences via variable-rate coding
Ziv, J., & Lempel, A. (1978) · IEEE Transactions on Information Theory · doi:10.1109/tit.1978.1055934 · Cited by 3,432
Valiant, L. G. (1984) · Communications of the ACM · doi:10.1145/1968.1972 · Cited by 3,279
Limits of Predictability in Human Mobility
Song, C., Qu, Z., Blumm, N., & Barabási, A.-L. (2010) · Science · doi:10.1126/science.1177170 · Cited by 3,234 · cited 1×
“[63], [64], whereas one of the implications of Table II is that the approach of entropy estimation via compression can be highly sub-optimal in large alpabet regimes.”
BackgroundPrediction and Entropy of Printed English
Shannon, C. E. (1951) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1951.tb01366.x · Cited by 2,686
Reliability of spike timing in neocortical neurons
Mainen, Z. F., & Sejnowski, T. J. (1995) · Science · doi:10.1126/science.7770778 · Cited by 1,950
Concentration Inequalities: A Nonasymptotic Theory of Independence
Boucheron, S., Lugosi, G., & Massart, P. (2013) · doi:10.1093/acprof:oso/9780199535255.001.0001 · Cited by 1,768 · cited 1×
“Indeed, as was illuminated by Donoho in [39], one of the blessings of high dimensionality is the “concentration of measure” [40] phenonmenon, which allows one to control the fluctuations of an estimator.”
BackgroundEstimation of entropy and mutual information
Paninski, L. (2003) · Neural Computation · doi:10.1162/089976603321780272 · Cited by 1,442 · cited 6×
“We thank Adel Javanmard for discussions related to constructing confidence intervals for high dimensional statistical problems, and Liam Paninski for interesting discussions related to Paninski [20].”
BackgroundMethodInfluentialStatistical Estimation and Optimal Recovery
Donoho, D. L. (1994) · The Annals of Statistics · doi:10.1214/aos/1176325367 · Cited by 263
How to Solve It: A New Aspect of Mathematical Method
POLYA, G. (2014) · doi:10.2307/j.ctvc773pk · Cited by 140
Cited by
Determining sequencing depth in a single-cell RNA-seq experiment
Zhang, M. J., Ntranos, V., & Tse, D. (2020) · Nature Communications · doi:10.1038/s41467-020-14482-y · Cited by 112
Toward Distributed Energy Services: Decentralizing Optimal Power Flow With Machine Learning
Dobbe, R., Sondermeijer, O., Fridovich-Keil, D., Arnold, D., Callaway, D., & Tomlin, C. (2020) · IEEE Transactions on Smart Grid · doi:10.1109/tsg.2019.2935711 · Cited by 120
Distributed Variational Representation Learning
Aguerri, I. E., & Zaidi, A. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2928806 · Cited by 84
“[45], [46], [47], [48] and references therein.”
Minimax Rates of Estimating Approximate Differential Privacy
Liu, X., & Oh, S. (2019) · arXiv · doi:10.48550/arxiv.1905.10335 · Cited by 4
Metadata
- Authors
- Jiao, J., Venkat, K., Han, Y., & Weissman, T.
- Venue
- IEEE Transactions on Information Theory
- Published
- 2015-05
- Volume
- 61
- Issue
- 5
- Pages
- 2835-2885
- ISSN
- 0018-9448 (ISSN-L)
- 1557-9654
- OpenAlex
- W1989151402
- Cited by
- 194
- References
- 10
- FWCI
- 19.86
- Type
- journal article
- Language
- en
- Open access
- green
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.