an:07204099
Zbl 07204099
Bertsimas, Dimitris; Li, Michael Lingzhi
Scalable holistic linear regression
EN
Oper. Res. Lett. 48, No. 3, 203-208 (2020).
00449462
2020
j
68 62
holistic linear regression; multicollinearity and significance in linear regression; mixed-integer optimization
Summary: We propose a new scalable algorithm for holistic linear regression building on \textit{D. Bertsimas} and \textit{A. King} [Oper. Res. 64, No. 1, 2--16 (2016; Zbl 1338.90272)]. Specifically, we develop new theory to model significance and multicollinearity as lazy constraints rather than checking the conditions iteratively. The resulting algorithm scales with the number of samples \(n\) in the 10,000s, compared to the low 100s in the previous framework. Computational results on real and synthetic datasets show it greatly improves from previous algorithms in accuracy, false detection rate, computational time and scalability.
Zbl 1338.90272