Two-Timescale Stochastic Approximation for Bilevel Optimisation Problems in Continuous-Time Models
Optimization and Control
2022-07-08 v2 Machine Learning
Abstract
We analyse the asymptotic properties of a continuous-time, two-timescale stochastic approximation algorithm designed for stochastic bilevel optimisation problems in continuous-time models. We obtain the weak convergence rate of this algorithm in the form of a central limit theorem. We also demonstrate how this algorithm can be applied to several continuous-time bilevel optimisation problems.
Cite
@article{arxiv.2206.06995,
title = {Two-Timescale Stochastic Approximation for Bilevel Optimisation Problems in Continuous-Time Models},
author = {Louis Sharrock},
journal= {arXiv preprint arXiv:2206.06995},
year = {2022}
}
Comments
Accepted at ICML 2022 Workshop on Continuous Time Methods in Machine Learning