Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 307

The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.

10.1162/jmlr.2003.3.4-5.951

·2000·CrossRef Listing of Deleted DOIs

Abstract

In this paper we study a paradigm to generalize online classification algorithms for binary classification problems to multiclass problems. The particular hypotheses we investigate maintain one prototype vector per class. Given an input instance, a multiclass hypothesis computes a similarity-score between each prototype and the input instance and sets the predicted label to be the index of the prototype achieving the highest similarity. To design and analyze the learning algorithms in this paper we introduce the notion of ultraconservativeness. Ultraconservative algorithms are algorithms that update only the prototypes attaining similarity-scores which are higher than the score of the correct label's prototype. We start by describing a family of additive ultraconservative algorithms where each algorithm in the family updates its prototypes by finding a feasible solution for a set of linear constraints that depend on the instantaneous similarity-scores. We then discuss a specific online algorithm that seeks a set of prototypes which have a small norm. The resulting algorithm, which we term MIRA (for Margin Infused Relaxed Algorithm) is ultraconservative as well. We derive mistake bounds for all the algorithms and provide further analysis of MIRA using a generalized notion of the margin for multiclass problems. We discuss the form the algorithms take in the binary case and show that all the algorithms from the first family reduce to the Perceptron algorithm while MIRA provides a new Perceptron-like algorithm with a margin-dependent learning rate. We then return to multiclass problems and describe an analogous multiplicative family of algorithms with corresponding mistake bounds. We end the formal part by deriving and analyzing a multiclass version of Li and Long's ROMMA algorithm. We conclude with a discussion of experimental results that demonstrate the merits of our algorithms.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1162/jmlr.2003.3.4-5.951

Cites

13 of 13 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 13 references

Research works printed but not linked: 8

  1. Cortes C., 1995, Machine Learning, 20, 273
  2. 10.1162/15324430260185628 · doi:10.1162/15324430260185628
  3. T. Friess, N. Cristianini, and C. Campbell. The kernel-adatron: A fast and simple learning procedure for support vector machines. In Machine Learning: Proceedings of the Fifteenth International Conference, 1998.
  4. 10.1162/15324430260185600 · doi:10.1162/15324430260185600
  5. Littlestone N., 1988, Machine Learning, 2, 285
  6. N. J. Nilsson. Learning Machines: Foundations of trainable pattern classification systems. McGraw-Hill, New York, 1965.
  7. J. R. Quinlan. C4.5: Programs for Machine Learning. Morgan Kaufmann, 1993.
  8. V. N. Vapnik. Statistical Learning Theory. Wiley, 1998.

Cited by

See all 307

Metadata

Venue
CrossRef Listing of Deleted DOIs
Published
2000
Volume
1
ISSN
0003-6951 (ISSN-L)
OpenAlex
W1714704734
Cited by
307
References
13
FWCI
3.33
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: 10.1162/jmlr.2003.3.4-5.951. https://app.cochat.ai/papers/10.1162/jmlr.2003.3.4-5.951
The paper
10.1162/jmlr.2003.3.4-5.951. (2000). CrossRef Listing of Deleted DOIs. https://doi.org/10.1162/jmlr.2003.3.4-5.951

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.