Best Subset Selection via a Modern Optimization Lens

Dimitris Bertsimas, Angela King, and Rahul Mazumder, Best Subset Selection via a Modern Optimization Lens, Annals of Statistics, 2016, Vol. 44, No. 2, 813–852.

In the period 1991–2015, algorithmic advances in Mixed Integer Optimization (MIO) coupled with hardware improvements have resulted in an astonishing 450 billion factor speedup in solving MIO problems. We present a MIO approach for solving the classical best subset selection problem of choosing k out of p features in linear regression given n observations. We develop a discrete extension of modern first-order continuous optimization methods to find high quality feasible solutions that we use as warm starts to a MIO solver that finds provably optimal solutions. The resulting algorithm (a) provides a solution with a guarantee on its suboptimality even if we terminate the algorithm early, (b) can accommodate side constraints on the coefficients of the linear regression and (c) extends to finding best subset solutions for the least absolute deviation loss function. Using a wide variety of synthetic and real datasets, we demonstrate that our approach solves problems with n in the 1000s and p in the 100s in minutes to provable optimality, and finds near optimal solutions for n in the 100s and p in the 1000s in minutes. We also establish via numerical experiments that the MIO approach performs better than Lasso and other popularly used sparse learning procedures, in terms of achieving sparse solutions with good predictive power.

Trevor Hastie, Robert Tibshirani, and Ryan J. Tibshiran, Extended Comparisons of Best Subset Selection, Forward Stepwise Selection, and the Lasso, arXiv:1707.08692 [stat.ME]. (Code in R. Solver Gurobi is free for academic users.)

The summary is roughly as follows: (a) neither best subset selection nor the lasso uniformly dominate the other, with best subset selection generally performing better in high signal-to-noise (SNR) ratio regimes, and the lasso better in low SNR regimes; (b) best subset selection and forward stepwise perform quite similarly throughout; (c) the relaxed lasso (actually, a simplified version of the original relaxed estimator defined in Meinshausen, 2007) is the overall winner, performing just about as well as the lasso in low SNR scenarios, and as well as best subset selection in high SNR scenarios.