Abstract
Qualitative but ordered random variables, such as severity of a pathology, are of paramount importance in biostatistics and medicine. Understanding the conditional distribution of such qualitative variables as a function of other explanatory variables can be performed using a specific regression model known as ordinal polytomous regression. Variable selection in the ordinal polytomous regression model is a computationally difficult combinatorial optimisation problem which is however crucial when practitioners need to understand which covariates are physically related to the output and which covariates are not. One easy way to circumvent the computational hardness of variable selection is to introduce a penalised maximum likelihood estimator based on some well chosen nonsmooth penalisation function such as, e.g., the l_1norm. In the case of the Gaussian linear model, the l_1penalised leastsquares estimator, also known as LASSO estimator, has attracted a lot of attention in the last decade, both from the theoretical and algorithmic viewpoints. However, even in the Gaussian linear model, accurate calibration of the relaxation parameter, i.e., the relative weight of the penalisation term in the estimation cost function is still considered a difficult problem that has to be addressed with caution. In the present paper, we apply l_1penalisation to the ordinal polytomous regression model and compare several hyperparameter calibration strategies. Our main contributions are: (a) a useful and simple l_1 penalised estimator for ordinal polytomous regression and a thorough description of how to apply Nesterov's accelerated gradient and the online FrankWolfe methods to the problem of computing this estimator, (b) a new hyperparameter calibration method for the proposed model, based on the QUT idea of Giacobino et al. and (c) a code which can be freely used that implements the proposed estimation procedure.
BibTeX  Entry
@InProceedings{chrtien_et_al:LIPIcs:2018:9319,
author = {St{\'e}phane Chr{\'e}tien and Christophe Guyeux and Serge Moulin},
title = {{l1Penalised Ordinal Polytomous Regression Estimators with Application to Gene Expression Studies}},
booktitle = {18th International Workshop on Algorithms in Bioinformatics (WABI 2018)},
pages = {17:117:13},
series = {Leibniz International Proceedings in Informatics (LIPIcs)},
ISBN = {9783959770828},
ISSN = {18688969},
year = {2018},
volume = {113},
editor = {Laxmi Parida and Esko Ukkonen},
publisher = {Schloss DagstuhlLeibnizZentrum fuer Informatik},
address = {Dagstuhl, Germany},
URL = {http://drops.dagstuhl.de/opus/volltexte/2018/9319},
URN = {urn:nbn:de:0030drops93199},
doi = {10.4230/LIPIcs.WABI.2018.17},
annote = {Keywords: LASSO, ordinal polytomous regression, Quantile Universal Threshold, FrankWolfe algorithm, Nesterov algorithm}
}
Keywords: 

LASSO, ordinal polytomous regression, Quantile Universal Threshold, FrankWolfe algorithm, Nesterov algorithm 
Seminar: 

18th International Workshop on Algorithms in Bioinformatics (WABI 2018) 
Issue Date: 

2018 
Date of publication: 

26.07.2018 