the archive
#mcmc
2 resultscs.LG2019
Bayesian Inference for Large Scale Image Classification
Jonathan Heek, Nal Kalchbrenner
The paper introduces ATMC, an adaptive noise MCMC algorithm for Bayesian inference in deep neural networks, and demonstrates its ability to improve classification accuracy and unce…
#bayesian inference#mcmc#image classification#deep learning
stat.ML2019
Posterior inference unchained with EL_2O
Uros Seljak, Byeonghee Yu
The paper proposes EL_2O, a noise‑free optimization of the L2 distance between an approximate log posterior and the true un‑normalized log posterior, offering faster and more accur…
#posterior inference#variational inference#mcmc#automatic differentiation