529. Direct Search Methods for Stochastic Zeroth-Order Problems
Invited abstract in session TB-1: Zeroth-Order Optimization Methods for Stochastic and Noisy Problems, stream Zeroth and first-order optimization methods.
Tuesday, 10:30-12:30Room: B100/1001
Authors (first author is the speaker)
| 1. | Francesco Rinaldi
|
| Dipartimento di Matematica "Tullio Levi-Civita", Università di Padova | |
| 2. | Andrea Cristofari
|
| Department of Civil Engineering and Computer Science Engineering, University of Rome "Tor Vergata" |
Abstract
In this talk, we describe a direct search algorithm that handles Stochastic Zeroth-Order problems, i.e., problems whose objective is not computable in practice, with the only information available obtained by a stochastic zeroth-order oracle calculating an estimate of the function for any given point.
Under standard assumptions on the accuracy and the variance of the random estimates used in the algorithm, we establish global convergence to stationary points. Finally, we report some numerical results to show the practical effectiveness of the method.
Keywords
- Derivative-free optimization
- Stochastic optimization
- Black-box optimization
Status: accepted
Back to the list of papers