Replica Exchange for Non-Convex Optimization
From MaRDI portal
Publication:6333350
arXiv2001.08356MaRDI QIDQ6333350FDOQ6333350
Authors: Jing Dong, Xin Thomson Tong 
Publication date: 22 January 2020
Abstract: Gradient descent (GD) is known to converge quickly for convex objective functions, but it can be trapped at local minima. On the other hand, Langevin dynamics (LD) can explore the state space and find global minima, but in order to give accurate estimates, LD needs to run with a small discretization step size and weak stochastic force, which in general slow down its convergence. This paper shows that these two algorithms and their non-swapping variants. can ``collaborate" through a simple exchange mechanism, in which they swap their current positions if LD yields a lower objective function. This idea can be seen as the singular limit of the replica-exchange technique from the sampling literature. We show that this new algorithm converges to the global minimum linearly with high probability, assuming the objective function is strongly convex in a neighborhood of the unique global minimum. By replacing gradients with stochastic gradients, and adding a proper threshold to the exchange mechanism, our algorithm can also be used in online settings. We also study non-swapping variants of the algorithm, which achieve similar performance. We further verify our theoretical results through some numerical experiments and observe superior performance of the proposed algorithm over running GD or LD alone.
This page was built for publication: Replica Exchange for Non-Convex Optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6333350)
