In many optimization problems arising from scientific, engineering and artificial intelligence
applications, objective and constraint functions are available only as the output of a black …

In this paper, we analyze several methods for approximating gradients of noisy functions
using only function values. These methods include finite differences, linear interpolation …

In this paper, we propose a stochastic optimization method that adaptively controls the
sample size used in the computation of gradient approximations. Unlike other variance …

In this paper, we develop convergence analysis of a modified line search method for
objective functions whose value is computed with noise and whose gradient estimates are …

Safe reinforcement learning (RL) is crucial for deploying RL agents in real-world
applications, as it aims to maximize long-term rewards while satisfying safety constraints …

We consider unconstrained optimization problems where only “stochastic” estimates of the
objective function are observable as replicates from a Monte Carlo oracle. The Monte Carlo …

Classical trust region methods were designed to solve problems in which function and
gradient information are exact. This paper considers the case when there are errors (or …

The multiobjective simulation optimization (MOSO) problem is a nonlinear multiobjective
optimization problem in which multiple simultaneous and conflicting objective functions can …

Optimizing parameterized quantum circuits is a key routine in using near-term quantum
devices. However, the existing algorithms for such optimization require an excessive …

Optimization lies at the heart of machine learning (ML) and signal processing (SP).
Contemporary approaches based on the stochastic gradient (SG) method are nonadaptive …