Empirical Analysis of Sampling Based Estimators for Evaluating RBMs
This work addresses the computational bottleneck in assessing RBM performance for researchers, but it is incremental as it compares existing methods without introducing new ones.
The paper tackled the problem of evaluating generative Restricted Boltzmann Machines (RBMs) by empirically comparing three sampling-based estimators for test log-likelihood, finding that the RAISE algorithm generally outperforms others on the MNIST dataset.
The Restricted Boltzmann Machines (RBM) can be used either as classifiers or as generative models. The quality of the generative RBM is measured through the average log-likelihood on test data. Due to the high computational complexity of evaluating the partition function, exact calculation of test log-likelihood is very difficult. In recent years some estimation methods are suggested for approximate computation of test log-likelihood. In this paper we present an empirical comparison of the main estimation methods, namely, the AIS algorithm for estimating the partition function, the CSL method for directly estimating the log-likelihood, and the RAISE algorithm that combines these two ideas. We use the MNIST data set to learn the RBM and then compare these methods for estimating the test log-likelihood.