Abstract

Quadratic regression involves modeling the response as a (generalized) linear function of not only the features , but also of quadratic terms . The inclusion of such higher-order “interaction terms" in regression often provides an easy way to increase accuracy in already-high-dimensional problems. However, this explodes the problem dimension from linear O(p) to quadratic O( ), and it is common to look for sparse interactions (typically via heuristics). In this paper we provide a new algorithm – Interaction Hard Thresholding (IntHT) – which is the first one to provably accurately solve this problem in sub-quadratic time and space. It is a variant of Iterative Hard Thresholding; one that uses the special quadratic structure to devise a new way to (approx.) extract the top elements of a size gradient in sub- time and space. Our main result is to theoretically prove that, in spite of the many speedup-related approximations, IntHT linearly converges to a consistent estimate under standard high-dimensional sparse recovery assumptions. We also demonstrate its value via synthetic experiments. Moreover, we numerically show that IntHT can be extended to higher-order regression problems, and also theoretically analyze an SVRG variant of IntHT.