Markov Chain Monte Carlo

Replica exchange stochastic gradient Langevin Dynamics

Introduced by Deng et al. in Non-convex Learning via Replica Exchange Stochastic Gradient MCMC

reSGLD proposes to simulate a high-temperature particle for exploration and a low-temperature particle for exploitation and allows them to swap simultaneously. Moreover, a correction term is included to avoid biases.

Source: Non-convex Learning via Replica Exchange Stochastic Gradient MCMC

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Image Classification 1 100.00%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories