ATMC, a new adaptive-noise MCMC sampler, is reported to outperform SGD baselines in accuracy, log-likelihood, and calibration on Cifar10 and ImageNet, and is claimed to be the first MCMC method to train a neural network on ImageNet.
Why is posterior sampling better than optimism for reinforcement learning? In Proceedings of the 34th International Conference on Machine Learning-Volume 70, pages 2701–2710
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Bayesian Inference for Large Scale Image Classification
ATMC, a new adaptive-noise MCMC sampler, is reported to outperform SGD baselines in accuracy, log-likelihood, and calibration on Cifar10 and ImageNet, and is claimed to be the first MCMC method to train a neural network on ImageNet.