On the Convergence of Bound Optimization Algorithms

Abstract

Many practitioners who use the EM algorithm complain that it is sometimes slow. When does this happen, and what can be done about it? In this paper, we study the general class of bound optimization algorithms - including Expectation-Maximization, Iterative Scaling and CCCP - and their relationship to direct optimization algorithms such as gradient-based methods for parameter learning. We derive a general relationship between the updates performed by bound optimization methods and those of gradient and second-order methods and identify analytic conditions under which bound optimization algorithms exhibit quasi-Newton behavior, and conditions under which they possess poor, first-order convergence. Based on this analysis, we consider several specific algorithms, interpret and analyze their convergence properties and provide some recipes for preprocessing input to these algorithms to yield faster convergence behavior. We report empirical results supporting our analysis and showing that simple data preprocessing can result in dramatically improved performance of bound optimizers in practice.

Appears in Proceedings of the Nineteenth Conference on Uncertainty in Artificial Intelligence (UAI2003)

Cited by in corpus (5)

• Optimization over Nonnegative and Convex Polynomials With and Without Semidefinite Programming
• Maximum Entropy Flow Networks
• Efficient Variational Bayes Learning of Graphical Models with Smooth Structural Changes
• Confidence-Constrained Maximum Entropy Framework for Learning from Multi-Instance Data
• PrivateMail: Supervised Manifold Learning of Deep Features With Differential Privacy for Image Retrieval