Sample Average Approximation for Black-Box Variational Inference
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.
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: Added changes suggested by reviewers.
Assigned Action Editor: ~Branislav_Kveton1
Submission Number: 1143
Loading