Improving Optimization-Based Approximate Inference by Clamping Variables

Abstract

While central to the application of probabilistic models to discrete data, the problem of marginal inference is in general intractable and efficient approximation schemes need to exploit the problem structure. Recently, there have been efforts to develop inference techniques that do not necessarily make factorization assumptions about the distribution, but… (More)

Topics

4 Figures and Tables

Cite this paper

@inproceedings{Zhao2017ImprovingOA, title={Improving Optimization-Based Approximate Inference by Clamping Variables}, author={Junyao Zhao and Josip Djolonga and Sebastian Tschiatschek and Andreas Krause}, booktitle={UAI}, year={2017} }