Learning RBM with a DC programming Approach
This work provides an incremental improvement in training RBMs, potentially benefiting researchers and practitioners in machine learning by offering faster convergence and better performance.
The paper tackled the problem of training Restricted Boltzmann Machines (RBMs) by formulating a stochastic difference of convex functions (DC) programming approach to minimize negative log-likelihood, showing that it reaches higher log-likelihood more rapidly than contrastive divergence for a given computational budget and is more efficient with centered gradients on benchmark datasets.
By exploiting the property that the RBM log-likelihood function is the difference of convex functions, we formulate a stochastic variant of the difference of convex functions (DC) programming to minimize the negative log-likelihood. Interestingly, the traditional contrastive divergence algorithm is a special case of the above formulation and the hyperparameters of the two algorithms can be chosen such that the amount of computation per mini-batch is identical. We show that for a given computational budget the proposed algorithm almost always reaches a higher log-likelihood more rapidly, compared to the standard contrastive divergence algorithm. Further, we modify this algorithm to use the centered gradients and show that it is more efficient and effective compared to the standard centered gradient algorithm on benchmark datasets.