Making Logistic Regression a Core Data Mining Tool with TR-IRLS

Authors:
Paul Komarek;Andrew W. Moore
Affiliations:
Carnegie Mellon University;Carnegie Mellon University
Venue:
ICDM '05 Proceedings of the Fifth IEEE International Conference on Data Mining
Year:
2005

Citing 2
Cited 6

Fitting Linear Models: An Application of Conjugate Gradient Algorithms

Fitting Linear Models: An Application of Conjugate Gradient Algorithms
An Introduction to the Conjugate Gradient Method Without the Agonizing Pain

An Introduction to the Conjugate Gradient Method Without the Agonizing Pain

Contextual advertising by combining relevance with click feedback

Proceedings of the 17th international conference on World Wide Web
Integrating genomic data and topological metrics to obtain reliable protein-protein interactions

FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 5
Learning from positive and unlabeled documents for retrieval of bacterial protein-protein interaction literature

ISMB/ECCB'09 Proceedings of the 2009 workshop of the BioLink Special Interest Group, international conference on Linking Literature, Information, and Knowledge for Biology
Collective context-aware topic models for entity disambiguation

Proceedings of the 21st international conference on World Wide Web
Scalable subspace logistic regression models for high dimensional data

APWeb'12 Proceedings of the 14th Asia-Pacific international conference on Web Technologies and Applications
Likelihood methods for point processes with refractoriness

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Binary classification is a core data mining task. For large datasets or real-time applications, desirable classifiersare accurate, fast, and need no parameter tuning. We present a simple implementation of logistic regression that meets these requirements. A combination of regularization, truncated Newton methods, and iteratively re-weighted least squares make it faster and more accurate than modern SVM implementations, and relatively insensitive to parameters. It is robust to linear dependencies and some scaling problems, making most data preprocessing unnecessary.