Efficient Meta Subspace Optimization

Author name not available (Why is that?)

Publication date: 28 October 2021

Abstract: Subspace optimization methods have the attractive property of reducing large-scale optimization problems to a sequence of low-dimensional subspace optimization problems. However, existing subspace optimization frameworks adopt a fixed update policy of the subspace and therefore appear to be sub-optimal. In this paper, we propose a new emph{Meta Subspace Optimization} (MSO) framework for large-scale optimization problems, which allows to determine the subspace matrix at each optimization iteration. In order to remain invariant to the optimization problem's dimension, we design an emph{efficient} meta optimizer based on very low-dimensional subspace optimization coefficients, inducing a rule-based method that can significantly improve performance. Finally, we design and analyze a reinforcement learning (RL) procedure based on the subspace optimization dynamics whose learnt policies outperform existing subspace optimization methods.

Has companion code repository: https://github.com/yoniLc/Meta-Subspace-Optimization

This page was built for publication: Efficient Meta Subspace Optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6381514)