Some Remarks on Replicated Simulated Annealing
This work provides theoretical analysis for a method aimed at improving robustness in neural network training, but it is incremental as it builds on existing ideas without introducing new paradigms.
The paper analyzes the replicated simulated annealing algorithm for training discrete weights neural networks, establishing convergence criteria and studying its sampling behavior, with experimental validation on synthetic and real datasets.
Recently authors have introduced the idea of training discrete weights neural networks using a mix between classical simulated annealing and a replica ansatz known from the statistical physics literature. Among other points, they claim their method is able to find robust configurations. In this paper, we analyze this so-called "replicated simulated annealing" algorithm. In particular, we explicit criteria to guarantee its convergence, and study when it successfully samples from configurations. We also perform experiments using synthetic and real data bases.