2018/01/08 by Enrique Romero Merino, Ferran Mazzanti Castrillejo, Merino, Enrique Romero +5 · 1 citation
Computer Science · Engineering · #FOS: Computer and information sciences #Lattice Boltzmann Simulation Studies #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and ELM #Neural and Evolutionary Computing (cs.NE) #Stochastic Gradient Optimization Techniques
paper · pdf · doi:10.48550/arxiv.1801.02567
openalex publication_date 2018/01/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.