A Stochastic Derivative-Free Optimization Method with Importance Sampling: Theory and Learning to Control
Name:
5727-Article Text-8952-1-10-20200513.pdf
Size:
3.201Mb
Format:
PDF
Description:
Conference Paper
Type
Conference PaperKAUST Department
Electrical Engineering ProgramElectrical Engineering
Physical Science and Engineering (PSE) Division
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Computer Science Program
Date
2020-04-03Permanent link to this record
http://hdl.handle.net/10754/653108
Metadata
Show full item recordAbstract
We consider the problem of unconstrained minimization of a smooth objective function in ℝn in a setting where only function evaluations are possible. While importance sampling is one of the most popular techniques used by machine learning practitioners to accelerate the convergence of their models when applicable, there is not much existing theory for this acceleration in the derivative-free setting. In this paper, we propose the first derivative free optimization method with importance sampling and derive new improved complexity results on non-convex, convex and strongly convex functions. We conduct extensive experiments on various synthetic and real LIBSVM datasets confirming our theoretical results. We test our method on a collection of continuous control tasks on MuJoCo environments with varying difficulty. Experiments show that our algorithm is practical for high dimensional continuous control problems where importance sampling results in a significant sample complexity improvement.Citation
Bibi, A., Bergou, E. H., Sener, O., Ghanem, B., & Richtarik, P. (2020). A Stochastic Derivative-Free Optimization Method with Importance Sampling: Theory and Learning to Control. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 3275–3282. doi:10.1609/aaai.v34i04.5727Sponsors
This work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research.arXiv
1902.01272Additional Links
https://aaai.org/ojs/index.php/AAAI/article/view/5727ae974a485f413a2113503eed53cd6c53
10.1609/aaai.v34i04.5727