Adaptive Sampling Quasi-Newton Methods for Derivative-Free Stochastic Optimization
This work addresses optimization problems in simulation and reinforcement learning, but it appears incremental as it builds on existing quasi-Newton methods with adaptive sampling.
The paper tackles stochastic zero-order optimization by proposing an adaptive sampling quasi-Newton method that estimates gradients using finite differences and controls sample sizes with modified tests, with preliminary numerical experiments showing potential performance benefits.
We consider stochastic zero-order optimization problems, which arise in settings from simulation optimization to reinforcement learning. We propose an adaptive sampling quasi-Newton method where we estimate the gradients of a stochastic function using finite differences within a common random number framework. We employ modified versions of a norm test and an inner product quasi-Newton test to control the sample sizes used in the stochastic approximations. We provide preliminary numerical experiments to illustrate potential performance benefits of the proposed method.