The DOI matches its Crossref record.
Sequential prediction of individual sequences under general loss functions
Abstract
We consider adaptive sequential prediction of arbitrary binary sequences when the performance is evaluated using a general loss function. The goal is to predict on each individual sequence nearly as well as the best prediction strategy in a given comparison class of (possibly adaptive) prediction strategies, called experts. By using a general loss function, we generalize previous work on universal prediction, forecasting, and data compression. However, here we restrict ourselves to the case when the comparison class is finite. For a given sequence, we define the regret as the total loss on the entire sequence suffered by the adaptive sequential predictor, minus the total loss suffered by the predictor in the comparison class that performs best on that particular sequence. We show that for a large class of loss functions, the minimax regret is either /spl theta/(log N) or /spl Omega/(/spl radic//spl Lscr/log N), depending on the loss function, where N is the number of predictors in the comparison class and/spl Lscr/ is the length of the sequence to be predicted. The former case was shown previously by Vovk (1990); we give a simplified analysis with an explicit closed form for the constant in the minimax regret formula, and give a probabilistic argument that shows this constant is the best possible. Some weak regularity conditions are imposed on the loss function in obtaining these results. We also extend our analysis to the case of predicting arbitrary sequences that take real values in the interval [0,1].
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Prediction, Learning, and Games
Cesa-Bianchi, N., & Lugosi, G. (2006) · Cambridge University Press eBooks · doi:10.1017/cbo9780511546921 · Cited by 3,162
Herbster, M., & Warmuth, M. K. (1998) · Machine Learning · doi:10.1023/a:1007424614876 · Cited by 560
Self-citationMerhav, N., & Feder, M. (1998) · IEEE Transactions on Information Theory · doi:10.1109/18.720534 · Cited by 438
On the Generalization Ability of On-Line Learning Algorithms
Cesa-Bianchi, N., Conconi, A., & Gentile, C. (2004) · IEEE Transactions on Information Theory · doi:10.1109/tit.2004.833339 · Cited by 426
Yang, Y. (2001) · Journal of the American Statistical Association · doi:10.1198/016214501753168262 · Cited by 312
Metadata
- Authors
- Haussler, D., Kivinen, J., & Warmuth, M. K.
- Venue
- IEEE Transactions on Information Theory
- Published
- 1998
- Volume
- 44
- Issue
- 5
- Pages
- 1906-1925
- ISSN
- 0018-9448 (ISSN-L)
- OpenAlex
- W2147632820
- Cited by
- 161
- References
- 0
- FWCI
- 13.74
- 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: Sequential prediction of individual sequences under general loss functions. https://app.cochat.ai/papers/10.1109/18.705569
- The paper
- Haussler, D., Kivinen, J., & Warmuth, M. K. (1998). Sequential prediction of individual sequences under general loss functions. IEEE Transactions on Information Theory. https://doi.org/10.1109/18.705569
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.