Linear-Sized Sparsifiers via Near-Linear Time Discrepancy Theory

Discrepancy theory provides powerful tools for producing higher-quality objects which "beat the union bound" in fundamental settings throughout combinatorics and computer science. However, this quality has often come at the price of more expensive algorithms. We introduce a new framework for bridging this gap, by allowing for the efficient implementation of discrepancy-theoretic primitives. Our framework repeatedly solves regularized optimization problems to low accuracy to approximate the partial coloring method of [Rot17], and simplifies and generalizes recent work of [JSS23] on fast algorithms for Spencer's theorem. In particular, our framework only requires that the discrepancy body of interest has exponentially large Gaussian measure and is expressible as a sublevel set of a symmetric, convex function. We combine this framework with new tools for proving Gaussian measure lower bounds to give improved algorithms for a variety of sparsification and coloring problems. As a first application, we use our framework to obtain an $\widetilde{O}(m \cdot ε^{-3.5})$ time algorithm for constructing an $ε$-approximate spectral sparsifier of an $m$-edge graph, matching the sparsity of [BSS14] up to constant factors and improving upon the $\widetilde{O}(m \cdot ε^{-6.5})$ runtime of [LeeS17]. We further give a state-of-the-art algorithm for constructing graph ultrasparsifiers and an almost-linear time algorithm for constructing linear-sized degree-preserving sparsifiers via discrepancy theory; in the latter case, such sparsifiers were not known to exist previously. We generalize these results to their analogs in sparsifying isotropic sums of positive semidefinite matrices. Finally, to demonstrate the versatility of our technique, we obtain a nearly-input-sparsity time constructive algorithm for Spencer's theorem (where we recover a recent result of [JSS23]).