Some Remarks on Replicated Simulated Annealing

Abstract

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.

References in corpus (10)

• Simulated Tempering: A New Monte Carlo Scheme
• BinaryConnect: Training Deep Neural Networks with binary weights during propagations
• PACT: Parameterized Clipping Activation for Quantized Neural Networks
• Learned Step Size Quantization
• Equi-energy sampler with applications in statistical inference and statistical mechanics
• Unreasonable Effectiveness of Learning Neural Networks: From Accessible States and Robust Ensembles to Basic Algorithmic Schemes
• Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks
• How to iron out rough landscapes and get optimal performances: Averaged Gradient Descent and its application to tensor PCA
• Rejoinder to "Equi-energy sampler with applications in statistical inference and statistical mechanics"
• Equi-Energy sampling does not converge rapidly on the mean-field Potts model with three colors close to the critical temperature