English

Automatic Differentiation of Some First-Order Methods in Parametric Optimization

Optimization and Control 2019-10-15 v1

Abstract

We aim at computing the derivative of the solution to a parametric optimization problem with respect to the involved parameters. For a class broader than that of strongly convex functions, this can be achieved by automatic differentiation of iterative minimization algorithms. If the iterative algorithm converges pointwise, then we prove that the derivative sequence also converges pointwise to the derivative of the minimizer with respect to the parameters. Moreover, we provide convergence rates for both sequences. In particular, we prove that the accelerated convergence rate of the Heavy-ball method compared to Gradient Descent also accelerates the derivative computation. An experiment with L2-Regularized Logistic Regression validates the theoretical results.

Keywords

Cite

@article{arxiv.1910.05696,
  title  = {Automatic Differentiation of Some First-Order Methods in Parametric Optimization},
  author = {Sheheryar Mehmood and Peter Ochs},
  journal= {arXiv preprint arXiv:1910.05696},
  year   = {2019}
}

Comments

22 pages, 1 figure, 1 table

R2 v1 2026-06-23T11:42:09.666Z