Wang, Yafei, Pan, Bo, Tu, Wei, Liu, Peng, Jiang, Bei, Gao, Chao, Lu, Wei, Jui, Shangling, Kong, Linglong (2022) Sample Average Approximation for Stochastic Optimization with Dependent Data: Performance Guarantees and Tractability. In: 36th AAAI Conference on Artificial Intelligence. . (Access to this publication is currently restricted. You may be able to access a copy if URLs are provided) (KAR id:91884)
PDF
Author's Accepted Manuscript
Language: English Restricted to Repository staff only |
|
Contact us about this Publication
|
|
Official URL: https://aaai.org/Symposia/Spring/sss22.php |
Abstract
Sample average approximation (SAA), a popular method for tractably solving stochastic optimization problems, enjoys strong asymptotic performance guarantees in settings with independent training samples. However, these guarantees are not known to hold generally with dependent samples, such as in online learning with time series data or distributed computing with Markovian training samples. In this paper, we show that SAA remains tractable when the distribution of unknown parameters is only observable through dependent instances and still enjoys asymptotic consistency and finite sample guarantees. Specifically, we provide a rigorous probability error analysis to derive $1 - \beta$ confidence bounds for the out-of-sample performance of SAA estimators and show that these estimators are asymptotically consistent. We then, using monotone operator theory, study the performance of a class of stochastic first-order algorithms trained on a dependent source of data. We show that approximation error for these algorithms is bounded and concentrates around zero, and establish deviation bounds for iterates when the underlying stochastic process is $\phi$-mixing. The algorithms presented can be used to handle numerically inconvenient loss functions such as the sum of a smooth and non-smooth function or of non-smooth functions with constraints. To illustrate the usefulness of our results, we present several stochastic versions of popular algorithms such as stochastic proximal gradient descent (S-PGD), stochastic relaxed Peaceman--Rachford splitting algorithms (S-rPRS), and numerical experiment.
Item Type: | Conference or workshop item (Paper) |
---|---|
Subjects: | Q Science > QA Mathematics (inc Computing science) > QA 75 Electronic computers. Computer science |
Divisions: | Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Mathematics, Statistics and Actuarial Science |
Depositing User: | Peng Liu |
Date Deposited: | 01 Dec 2021 16:27 UTC |
Last Modified: | 05 Nov 2024 12:57 UTC |
Resource URI: | https://kar.kent.ac.uk/id/eprint/91884 (The current URI for this page, for reference purposes) |
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):