Competitive On‐line Statistics
The DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.
Abstract
Summary: A radically new approach to statistical modelling, which combines mathematical techniques of Bayesian statistics with the philosophy of the theory of competitive on‐line algorithms, has arisen over the last decade in computer science (to a large degree, under the influence of Dawid's prequential statistics). In this approach, which we call “competitive on‐line statistics”, it is not assumed that data are generated by some stochastic mechanism; the bounds derived for the performance of competitive on‐line statistical procedures are guaranteed to hold (and not just hold with high probability or on the average). This paper reviews some results in this area; the new material in it includes the proofs for the performance of the Aggregating Algorithm in the problem of linear regression with square loss.
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
A decision-theoretic generalization of on-line learning and an application to boosting
Freund, Y., & Schapire, R. E. (1997) · Journal of Computer and System Sciences · doi:10.1006/jcss.1997.1504 · Cited by 20,466
Draper, N. R., & Smith, H. (1998) · Wiley Series in Probability and Statistics · doi:10.1002/9781118625590 · Cited by 5,024
The Weighted Majority Algorithm
Littlestone, N., & Warmuth, M. K. (1994) · Information and Computation · doi:10.1006/inco.1994.1009 · Cited by 1,975
An Introduction to Kolmogorov Complexity and Its Applications
Li, M., & Vitányi, P. (1997) · Springer eBooks · doi:10.1007/978-1-4757-2606-0 · Cited by 1,775 · cited 3×
“4 Predictive complexity A recent application of the Aggregating Algorithm is to generalize the notion of Kolmogorov complexity (Li and Vitanyi [44] is an excellent review of the latter).”
InfluentialA formal theory of inductive inference. Part II
Solomonoff, R. J. (1964) · Information and Control · doi:10.1016/s0019-9958(64)90131-7 · Cited by 1,758
A Universal Prior for Integers and Estimation by Minimum Description Length
Rissanen, J. (1983) · The Annals of Statistics · doi:10.1214/aos/1176346150 · Cited by 1,672 · cited 1×
“Following Rissanen [49], we can instead take “computable approximations” to the universal enumerable semimeasure.”
MethodA formal theory of inductive inference. Part I
Solomonoff, R. J. (1964) · Information and Control · doi:10.1016/s0019-9958(64)90223-2 · Cited by 1,192
Dawid, A. P. (1984) · Journal of the Royal Statistical Society. Series A (General) · doi:10.2307/2981683 · Cited by 1,085
An Information Measure for Classification
Wallace, C. S., & Boulton, D. M. (1968) · The Computer Journal · doi:10.1093/comjnl/11.2.185 · Cited by 933 · cited 1×
“These terms are analogous to the term n2 ln T occurring in the analysis of the log-loss game and its generalizations, in particular in Rissanen’s theory of stochastic complexity ([50]; extended to more general loss functions by Yamanishi [72]), Wallace’s theory of minimum message length (Wallace and Boulton [69], Wall…”
BackgroundCover, T. M. (1991) · Mathematical Finance · doi:10.1111/j.1467-9965.1991.tb00002.x · Cited by 898 · cited 1×
“) Cover’s “universal portfolio” algorithm [17, 18] is the AA applied to this game and a particular decision pool, the constant rebalanced portfolios (cf.”
Method
Cited by
A primal-dual perspective of online learning algorithms
Shalev-Shwartz, S., & Singer, Y. (2007) · Machine Learning · doi:10.1007/s10994-007-5014-x · Cited by 168
“[17,5,23]).”
MethodThe Fundamental Nature of the Log Loss Function
Vovk, V. (2015) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-23534-9_20 · Cited by 71
“loss function λ is called mixable if the set n (u,v) ∈ [0,1]2 | ∃p ∈ [0,1] : u ≤ e−ηλ(p,0),v ≤ e−ηλ(p,1) o is convex for some η ∈ (0,∞). Both the log and Brier loss functions are mixable (see, e.g., [3], Section 2). All proper mixable loss functions are strictly proper. 3 Repetitive predictions Starting from this sect…”
BackgroundSelf-citationZhu, M., Zecchin, M., Park, S., Guo, C., Feng, C., Popovski, P., & Simeone, O. (2025) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3549222 · Cited by 6
Metadata
- Authors
- Vovk, V.
- Venue
- International Statistical Review
- Publisher
- Wiley
- Published
- 2001-08
- Volume
- 69
- Issue
- 2
- Pages
- 213-248
- ISSN
- 0306-7734 (ISSN-L)
- 1751-5823
- OpenAlex
- W2139716865
- Cited by
- 216
- References
- 42
- FWCI
- 9.41
- Type
- journal article
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Competitive On‐line Statistics. https://app.cochat.ai/papers/10.1111/j.1751-5823.2001.tb00457.x
- The paper
- Vovk, V. (2001). Competitive On‐line Statistics. International Statistical Review. https://doi.org/10.1111/j.1751-5823.2001.tb00457.x
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.