A Bayesian boosting theorem
Richard Nock,Marc Sebban +1 more
7
TL;DR: The first theorem of (R.E. Singer) bounding the error of the A da B oost boosting algorithm, to integrate Bayes risk is refined, suggesting the significant time savings could be obtained on some domains without damaging the solution.
read more
About: This article is published in Pattern Recognition Letters. The article was published on 01 Mar 2001. and is currently open access. The article focuses on the topics: BrownBoost & Boosting (machine learning).
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A simple locally adaptive nearest neighbor rule with application to pollution forecasting
TL;DR: The reasons for the rule's efficiency, methods for speeding-up the classification time, and derive from the sNN rule a reliable and fast algorithm to fix the parameter k in the k-NN rule, a longstanding problem in this field are discussed.
Boosting One-Class Support Vector Machines for Multi-Class Classification
TL;DR: A multi- class classification algorithm is developed by incorporating one-class SVMs with a well-designed discriminant function and outperforms other multi-class algorithms, such as support vector data descriptions (SVDDs) and AdaBoost.M1.
23
Exploration of a hybrid feature selection algorithm
TL;DR: This paper presents and explores a new hybrid approach, ChiBlur, which involves the use of concepts from both the blurring and χ2-based approaches to feature selection, as well as concepts from multi-objective optimization.
16
On boosting improvement: error reduction and convergence speed-up
Marc Sebban,Henri-Maxime Suchier +1 more
- 22 Sep 2003
TL;DR: This article proposes a slight modification of the weight update rule of the algorithm ADABOOST, and shows that by exploiting an adaptive measure of a local entropy, computed from a neighborhood graph built on the examples, it is possible to identify not only the outliers but also the examples located in the Bayesian error region.
6
Extending the Boosting Framework based on Bayesian Methodology
Wei Xu
- 31 Mar 2023
TL;DR: In this paper , a bayesian-based approach to Boosting is presented, in which a variablenauswahl in der Analyse von hochdimensionalen Datensätzen ermöglicht, nämlätzliche Flexibilität bietet, um verschiedene Arten von additiven Regressionstermen zu schätze.
References
The Strength of Weak Learnability
TL;DR: In this paper, a method is described for converting a weak learning algorithm into one that achieves arbitrarily high accuracy, and it is shown that these two notions of learnability are equivalent.
Improved boosting algorithms using confidence-rated predictions
Robert E. Schapire,Yoram Singer +1 more
- 24 Jul 1998
TL;DR: Several improvements to Freund and Schapire’s AdaBoost boosting algorithm are described, particularly in a setting in which hypotheses may assign confidences to each of their predictions.
On the Boosting Ability of Top-Down Decision Tree Learning Algorithms
Michael Kearns,Yishay Mansour +1 more
TL;DR: This work analyzes the performance of top?down algorithms for decision tree learning and proves that some popular and empirically successful heuristics that are base on first principles meet the criteria of an independently motivated theoretical model.
221
On the boosting ability of top-down decision tree learning algorithms
Michael Kearns,Yishay Mansour +1 more
- 01 Jul 1996
TL;DR: This work analyzes the performance of top-down algorithms for decision tree learning and proves that some popular and empirically successful heuristics that are based on first principles meet the criteria of an independently motivated theoretical model.
166
Related Papers (5)
Ajay Jasra,Christopher Holmes +1 more
[...]
João Gama
- 27 Jan 2003
Hugh A. Chipman,Edward I. George,Robert E. McCulloch +2 more
- 04 Dec 2006