Reddy, D. Sai Koti ; Prashanth, L.A. ; Bhatnagar, Shalabh (2016) Improved Hessian estimation for adaptive random directions stochastic approximation In: IEEE 55th Conference on Decision and Control (CDC), 12-14 Dec. 2016, Las Vegas, NV, USA.
Full text not available from this repository.
Official URL: http://doi.org/10.1109/CDC.2016.7798823
Related URL: http://dx.doi.org/10.1109/CDC.2016.7798823
Abstract
We propose an improved Hessian estimation scheme for the second-order random directions stochastic approximation (2RDSA) algorithm [1]. The proposed scheme, inspired by [2], reduces the error in the Hessian estimate by (i) incorporating a zero-mean feedback term; and (ii) optimizing the step-sizes used in the Hessian recursion of 2RDSA.We prove that 2RDSA with our Hessian improvement scheme (2RDSA-IH) converges asymptotically to the true Hessian. The advantage with 2RDSA-IH is that it requires only 75% of the simulation cost per-iteration for 2SPSA with improved Hessian estimation (2SPSA-IH) [2]. Numerical experiments show that 2RDSA-IH outperforms both 2SPSA-IH and 2RDSA without the improved Hessian estimation scheme.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Source: | Copyright of this article belongs to Institute of Electrical and Electronics Engineers. |
| ID Code: | 116648 |
| Deposited On: | 12 Apr 2021 07:17 |
| Last Modified: | 12 Apr 2021 07:17 |
Repository Staff Only: item control page
