Sparse Logistic Regression with Lp Penalty for Biomarker Identification

2007 ◽  
Vol 6 (1) ◽  
Author(s):  
Zhenqiu Liu ◽  
Feng Jiang ◽  
Guoliang Tian ◽  
Suna Wang ◽  
Fumiaki Sato ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Microarray Data ◽  
High Dimensional ◽  
Computational Results ◽  
Smooth Approximation ◽  
Biomarker Identification ◽  
Sparse Logistic Regression ◽  
Regularization Parameters ◽  
Novel Method ◽  
Convex Regularization

In this paper, we propose a novel method for sparse logistic regression with non-convex regularization Lp (p <1). Based on smooth approximation, we develop several fast algorithms for learning the classifier that is applicable to high dimensional dataset such as gene expression. To the best of our knowledge, these are the first algorithms to perform sparse logistic regression with an Lp and elastic net (Le) penalty. The regularization parameters are decided through maximizing the area under the ROC curve (AUC) of the test data. Experimental results on methylation and microarray data attest the accuracy, sparsity, and efficiency of the proposed algorithms. Biomarkers identified with our methods are compared with that in the literature. Our computational results show that Lp Logistic regression (p <1) outperforms the L1 logistic regression and SCAD SVM. Software is available upon request from the first author.

scholarly journals An Additive Sparse Logistic Regularization Method for Cancer Classification in Microarray Data

2021 ◽  
Vol 18 (2) ◽  
Keyword(s):  
Logistic Regression ◽  
Microarray Data ◽  
High Dimensional ◽  
Cancer Data ◽  
Abnormal Growth ◽  
Sparse Logistic Regression ◽  
Genome Data ◽  
Regularization Techniques ◽  
Performance Of Algorithm

Now a day’s cancer has become a deathly disease due to the abnormal growth of the cell. Many researchers are working in this area for the early prediction of cancer. For the proper classification of cancer data, demands for the identification of proper set of genes by analyzing the genomic data. Most of the researchers used microarrays to identify the cancerous genomes. However, such kind of data is high dimensional where number of genes are more compared to samples. Also the data consists of many irrelevant features and noisy data. The classification technique deal with such kind of data influences the performance of algorithm. A popular classification algorithm (i.e., Logistic Regression) is considered in this work for gene classification. Regularization techniques like Lasso with L1 penalty, Ridge with L2 penalty, and hybrid Lasso with L1/2+2 penalty used to minimize irrelevant features and avoid overfitting. However, these methods are of sparse parametric and limits to linear data. Also methods have not produced promising performance when applied to high dimensional genome data. For solving these problems, this paper presents an Additive Sparse Logistic Regression with Additive Regularization (ASLR) method to discriminate linear and non-linear variables in gene classification. The results depicted that the proposed method proved to be the best-regularized method for classifying microarray data compared to standard methods

scholarly journals A Knowledge Transfer Framework for Differentially Private Sparse Learning

2020 ◽  
Vol 34 (04) ◽  
pp. 6235-6242
Author(s):  
Lingxiao Wang ◽  
Quanquan Gu
Keyword(s):  
Logistic Regression ◽  
Linear Regression ◽  
Knowledge Transfer ◽  
Linear Convergence ◽  
High Dimensional ◽  
Sparse Learning ◽  
Real World Data ◽  
Linear Convergence Rate ◽  
Sparse Logistic Regression ◽  
Learning Framework

We study the problem of estimating high dimensional models with underlying sparse structures while preserving the privacy of each training example. We develop a differentially private high-dimensional sparse learning framework using the idea of knowledge transfer. More specifically, we propose to distill the knowledge from a “teacher” estimator trained on a private dataset, by creating a new dataset from auxiliary features, and then train a differentially private “student” estimator using this new dataset. In addition, we establish the linear convergence rate as well as the utility guarantee for our proposed method. For sparse linear regression and sparse logistic regression, our method achieves improved utility guarantees compared with the best known results (Kifer, Smith and Thakurta 2012; Wang and Gu 2019). We further demonstrate the superiority of our framework through both synthetic and real-world data experiments.

Sign in / Sign up

Export Citation Format

Share Document