Projects per year
Abstract
We propose an alternative parameterization of Logistic Regression (LR) for the categorical data, multi-class setting. LR optimizes the conditional log-likelihood over the training data and is based on an iterative optimization procedure to tune this objective function. The optimization procedure employed may be sensitive to scale and hence an effective pre-conditioning method is recommended. Many problems in machine learning involve arbitrary scales or categorical data (where simple standardization of features is not applicable). The problem can be alleviated by using optimization routines that are invariant to scale such as (second-order) Newton methods. However, computing and inverting the Hessian is a costly procedure and not feasible for big data. Thus one must often rely on first-order methods such as gradient descent (GD), stochastic gradient descent (SGD) or approximate second-order such as quasi-Newton (QN) routines, which are not invariant to scale. This paper proposes a simple yet effective pre-conditioner for speeding-up LR based on naive Bayes conditional probability estimates. The idea is to scale each attribute by the log of the conditional probability of that attribute given the class. This formulation substantially speeds-up LR's convergence. It also provides a weighted naive Bayes formulation which yields an effective framework for hybrid generative-discriminative classification.
Original language | English |
---|---|
Title of host publication | Proceedings, 14th IEEE International Conference on Data Mining (ICDM 2014) |
Editors | Ravi Kumar, Hannu Toivonen, Jian Pei, Joshua Zhexue Huang, Xindong Wu |
Place of Publication | Los Alamitos CA USA |
Publisher | IEEE, Institute of Electrical and Electronics Engineers |
Pages | 1097-1102 |
Number of pages | 6 |
ISBN (Electronic) | 9781479943029 |
ISBN (Print) | 9781479943029 |
DOIs | |
Publication status | Published - 2014 |
Event | IEEE International Conference on Data Mining 2014 - Shenzhen, China Duration: 14 Dec 2014 → 17 Dec 2014 Conference number: 14th http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=7022262 (Conference Proceedings) |
Publication series
Name | Proceedings - IEEE International Conference on Data Mining, ICDM |
---|---|
Number | January |
Volume | 2015-January |
ISSN (Print) | 1550-4786 |
Conference
Conference | IEEE International Conference on Data Mining 2014 |
---|---|
Abbreviated title | ICDM 2014 |
Country/Territory | China |
City | Shenzhen |
Period | 14/12/14 → 17/12/14 |
Internet address |
|
Keywords
- classification
- discriminative-generative learning
- logistic regression
- pre-conditioning
- stochastic gradient descent
- weighted naive Bayes
Projects
- 1 Finished