Zrnic, Tijana and Mazumdar, Eric (2022) A Note on Zeroth-Order Optimization on the Simplex. . (Unpublished) https://resolver.caltech.edu/CaltechAUTHORS:20221220-221907545
Full text is not posted in this repository. Consult Related URLs below.
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20221220-221907545
Abstract
We construct a zeroth-order gradient estimator for a smooth function defined on the probability simplex. The proposed estimator queries the simplex only. We prove that projected gradient descent and the exponential weights algorithm, when run with this estimator instead of exact gradients, converge at a O(T^(-1/4)}) rate.
| Item Type: | Report or Paper (Discussion Paper) | ||||||
|---|---|---|---|---|---|---|---|
| Related URLs: |
| ||||||
| ORCID: |
| ||||||
| Record Number: | CaltechAUTHORS:20221220-221907545 | ||||||
| Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20221220-221907545 | ||||||
| Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. | ||||||
| ID Code: | 118519 | ||||||
| Collection: | CaltechAUTHORS | ||||||
| Deposited By: | George Porter | ||||||
| Deposited On: | 21 Dec 2022 19:35 | ||||||
| Last Modified: | 21 Dec 2022 19:35 |
Repository Staff Only: item control page
