Weighted Contrastive Divergence
This work addresses a specific bottleneck in energy-based models for machine learning practitioners, offering an incremental but effective enhancement to existing algorithms.
The paper tackles the computational inefficiency and gradient approximation issues in learning Restricted Boltzmann Machines via Contrastive Divergence (CD), proposing Weighted CD (WCD) as a new algorithm that shows significant improvement over standard and persistent CD with minimal added computational cost.
Learning algorithms for energy based Boltzmann architectures that rely on gradient descent are in general computationally prohibitive, typically due to the exponential number of terms involved in computing the partition function. In this way one has to resort to approximation schemes for the evaluation of the gradient. This is the case of Restricted Boltzmann Machines (RBM) and its learning algorithm Contrastive Divergence (CD). It is well-known that CD has a number of shortcomings, and its approximation to the gradient has several drawbacks. Overcoming these defects has been the basis of much research and new algorithms have been devised, such as persistent CD. In this manuscript we propose a new algorithm that we call Weighted CD (WCD), built from small modifications of the negative phase in standard CD. However small these modifications may be, experimental work reported in this paper suggest that WCD provides a significant improvement over standard CD and persistent CD at a small additional computational cost.