AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Replica-Exchange Nos\'e-Hoover Dynamics for Bayesian Learning on Large Datasets

Rui Luo, Qiang Zhang, Yaodong Yang, Jun Wang

NeurIPS 2020 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Nonparametric and PAC-Bayes Bayesian learning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use RENHD instead of TACT-HMCLSTM RNN Bayesian sampler · Fashion-MNIST, 0% permuted labelsaccuracy: 89.74 \pm 0.13\,\% -> 90.87 \pm 0.12\,\%Improved
Use RENHD instead of TACT-HMCLSTM RNN Bayesian sampler · Fashion-MNIST, 20% permuted labelsaccuracy: 88.83 \pm 0.17\,\% -> 89.45 \pm 0.17\,\%Improved
Use RENHD instead of TACT-HMCLSTM RNN Bayesian sampler · Fashion-MNIST, 30% permuted labelsaccuracy: 88.78 \pm 0.17\,\% -> 89.06 \pm 0.16\,\%Improved
Use RENHD instead of TACT-HMCResNet Bayesian sampler · CIFAR-10, 0% permuted labelsaccuracy: 88.01 \pm 0.13\,\% -> 88.41 \pm 0.12\,\%Improved
Use RENHD instead of TACT-HMCResNet Bayesian sampler · CIFAR-10, 20% permuted labelsaccuracy: 82.28 \pm 0.13\,\% -> 84.48 \pm 0.14\,\%Improved
Use RENHD instead of TACT-HMCResNet Bayesian sampler · CIFAR-10, 30% permuted labelsaccuracy: 79.43 \pm 0.12\,\% -> 82.65 \pm 0.13\,\%Improved
Use RENHD instead of TACT-HMCBayesian sampler · Real-image experiments, same execution timeunbiased multimodal samples: 4 timesImproved
Use the analytic compensation distribution rather than the numerical solutionReplica-exchange acceptance protocol · Samplingsampling speed: 20\timesImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy