- Title
- A fast quasi-Newton-type method for large-scale stochastic optimisation
- Creator
- Wills, Adrian; Schön, Thomas B.; Jidling, Carl
- Relation
- IFAC-PapersOnLine Vol. 53, Issue 2, p. 1249-1254
- Publisher Link
- http://dx.doi.org/10.1016/j.ifacol.2020.12.1849
- Publisher
- Elsevier
- Resource Type
- journal article
- Date
- 2020
- Description
- In recent years there has been an increased interest in stochastic adaptations of limited memory quasi-Newton methods, which compared to pure gradient-based routines can improve the convergence by incorporating second-order information. In this work we propose a direct least-squares approach conceptually similar to the limited memory quasi-Newton methods, but that computes the search direction in a slightly different way. This is achieved in a fast and numerically robust manner by maintaining a Cholesky factor of low dimension. The performance is demonstrated on real-world benchmark problems which shows improved results in comparison with already established methods.
- Subject
- optimisation problems; large-scale problems; stochastic systems; Cholesky factorisation; neural networks
- Identifier
- http://hdl.handle.net/1959.13/1442525
- Identifier
- uon:41712
- Identifier
- ISSN:2405-8963
- Language
- eng
- Reviewed
- Hits: 957
- Visitors: 955
- Downloads: 0
Thumbnail | File | Description | Size | Format |
---|