Discrete-Convex-Analysis-Based Framework for Warm-Starting Algorithms with PredictionsDownload PDF

Published: 31 Oct 2022, Last Modified: 07 Oct 2022NeurIPS 2022 AcceptReaders: Everyone
Keywords: combinatorial optimization, discrete convex analysis, algorithms with predictions, time complexity
TL;DR: We present a principled discrete-convex-analysis-based framework for warm-starting algorithms with predictions to improve time complexity bounds.
Abstract: Augmenting algorithms with learned predictions is a promising approach for going beyond worst-case bounds. Dinitz, Im, Lavastida, Moseley, and Vassilvitskii~(2021) have demonstrated that warm-starts with learned dual solutions can improve the time complexity of the Hungarian method for weighted perfect bipartite matching. We extend and improve their framework in a principled manner via \textit{discrete convex analysis} (DCA), a discrete analog of convex analysis. We show the usefulness of our DCA-based framework by applying it to weighted perfect bipartite matching, weighted matroid intersection, and discrete energy minimization for computer vision. Our DCA-based framework yields time complexity bounds that depend on the $\ell_\infty$-distance from a predicted solution to an optimal solution, which has two advantages relative to the previous $\ell_1$-distance-dependent bounds: time complexity bounds are smaller, and learning of predictions is more sample efficient. We also discuss whether to learn primal or dual solutions from the DCA perspective.
Supplementary Material: pdf
9 Replies