A fast algorithm for separated sparsity via perturbed lagrangians
Author(s)
Madry, A; Mitrović, S; Schmidt, L
DownloadPublished version (541.0Kb)
Open Access Policy
Open Access Policy
Creative Commons Attribution-Noncommercial-Share Alike
Terms of use
Metadata
Show full item recordAbstract
Copyright 2018 by the author(s). Sparsity-based methods are widely used in machine learning, statistics, and signal processing. There is now a rich class of structured sparsity approaches that expand the modeling power of the sparsity paradigm and incorporate constraints such as group sparsity, graph sparsity, or hierarchical sparsity. While these sparsity models offer improved sample complexity and better interpretability, the improvements come at a computational cost: it is often challenging to optimize over the (non-convex) constraint sets that capture various sparsity structures. In this paper, we make progress in this direction in the context of separated sparsity – a fundamental sparsity notion that captures exclusion constraints in linearly ordered data such as time series. While prior algorithms for computing a projection onto this constraint set required quadratic time, we provide a perturbed Lagrangian relaxation approach that computes provably exact projection in only nearly-linear time. Although the sparsity constraint is non-convex, our perturbed Lagrangian approach is still guaranteed to find a globally optimal solution. In experiments, our new algorithms offer a 10× speed-up already on moderately-size inputs.
Date issued
2018Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science; Massachusetts Institute of Technology. Computer Science and Artificial Intelligence LaboratoryJournal
International Conference on Artificial Intelligence and Statistics, AISTATS 2018
Citation
Madry, A, Mitrović, S and Schmidt, L. 2018. "A fast algorithm for separated sparsity via perturbed lagrangians." International Conference on Artificial Intelligence and Statistics, AISTATS 2018, 84.
Version: Final published version