The Information Bottleneck EM Algorithm
This addresses a central challenge in probabilistic graphical models with implications for real-life problems, though it appears incremental as it builds on the EM algorithm.
The paper tackles the problem of learning with hidden variables in probabilistic graphical models, which often gets trapped in local maxima with the Expectation Maximization (EM) algorithm, by introducing the Information Bottleneck EM (IB-EM) algorithm that finds superior solutions.
Learning with hidden variables is a central challenge in probabilistic graphical models that has important implications for many real-life problems. The classical approach is using the Expectation Maximization (EM) algorithm. This algorithm, however, can get trapped in local maxima. In this paper we explore a new approach that is based on the Information Bottleneck principle. In this approach, we view the learning problem as a tradeoff between two information theoretic objectives. The first is to make the hidden variables uninformative about the identity of specific instances. The second is to make the hidden variables informative about the observed attributes. By exploring different tradeoffs between these two objectives, we can gradually converge on a high-scoring solution. As we show, the resulting, Information Bottleneck Expectation Maximization (IB-EM) algorithm, manages to find solutions that are superior to standard EM methods.