English

Linear Regression without Correspondences via Concave Minimization

Information Theory 2020-09-15 v2 Machine Learning math.IT

Abstract

Linear regression without correspondences concerns the recovery of a signal in the linear regression setting, where the correspondences between the observations and the linear functionals are unknown. The associated maximum likelihood function is NP-hard to compute when the signal has dimension larger than one. To optimize this objective function we reformulate it as a concave minimization problem, which we solve via branch-and-bound. This is supported by a computable search space to branch, an effective lower bounding scheme via convex envelope minimization and a refined upper bound, all naturally arising from the concave minimization reformulation. The resulting algorithm outperforms state-of-the-art methods for fully shuffled data and remains tractable for up to 88-dimensional signals, an untouched regime in prior work.

Keywords

Cite

@article{arxiv.2003.07706,
  title  = {Linear Regression without Correspondences via Concave Minimization},
  author = {Liangzu Peng and Manolis C. Tsakiris},
  journal= {arXiv preprint arXiv:2003.07706},
  year   = {2020}
}
R2 v1 2026-06-23T14:17:23.655Z