pith. machine review for the scientific record. sign in

arxiv: 1606.01885 · v1 · submitted 2016-06-06 · 💻 cs.LG · cs.AI· math.OC· stat.ML

Recognition: unknown

Learning to Optimize

Authors on Pith no claims yet
classification 💻 cs.LG cs.AImath.OCstat.ML
keywords algorithmoptimizationdesignlearnlearningmethodpolicyalgorithms
0
0 comments X
read the original abstract

Algorithm design is a laborious process and often requires many iterations of ideation and validation. In this paper, we explore automating algorithm design and present a method to learn an optimization algorithm, which we believe to be the first method that can automatically discover a better algorithm. We approach this problem from a reinforcement learning perspective and represent any particular optimization algorithm as a policy. We learn an optimization algorithm using guided policy search and demonstrate that the resulting algorithm outperforms existing hand-engineered algorithms in terms of convergence speed and/or the final objective value.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Regret Equals Covariance: A Closed-Form Characterization for Stochastic Optimization

    econ.EM 2026-05 unverdicted novelty 6.0

    Expected regret equals covariance between costs and optimal decisions for linear and quadratic stochastic programs, with explicit bounds on the residual.

  2. Learning to Cut: Reinforcement Learning for Benders Decomposition

    math.OC 2026-05 unverdicted novelty 6.0

    RLBD trains a neural policy with REINFORCE to select cuts adaptively in Benders decomposition, yielding faster convergence and better generalization than standard BD or SVM-based LearnBD on an EV charging problem.

  3. Learning to Test: Physics-Informed Representation for Dynamical Instability Detection

    cs.LG 2026-04 unverdicted novelty 6.0

    A physics-informed neural representation is learned from safe data to support distributional hypothesis testing for dynamical instability in stochastic DAE systems without repeated simulations.