Sample Average Approximation for Black-Box VIDownload PDFOpen Website

Published: 01 Jan 2023, Last Modified: 08 May 2023CoRR 2023Readers: Everyone
Abstract: We present a novel approach for black-box VI that bypasses the difficulties of stochastic gradient ascent, including the task of selecting step-sizes. Our approach involves using a sequence of sample average approximation (SAA) problems. SAA approximates the solution of stochastic optimization problems by transforming them into deterministic ones. We use quasi-Newton methods and line search to solve each deterministic optimization problem and present a heuristic policy to automate hyperparameter selection. Our experiments show that our method simplifies the VI problem and achieves faster performance than existing methods.
0 Replies

Loading