AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

An Adaptive Empirical Bayesian Method for Sparse Deep Learning

Wei Deng, Xiao Zhang, Faming Liang, Guang Lin

NeurIPS 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Sequential Monte Carlo for inference · 31 citations (OpenAlex)

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
adapt SSGL priors with stochastic approximation instead of fixing the latent priors (ablation)SGHMC on MNIST · MNISTaccuracy: 99.47 -> 99.59Improved
adapt SSGL priors with stochastic approximation instead of fixing the latent priors (ablation)SGHMC on FMNIST · FMNISTaccuracy: 92.88 -> 93.01Improved
add stochastic approximation updates for latent variables rather than the fixed-step SGLD-EM update (ablation)SGLD-EM · Linear regression simulation test set (v0=0.1, σ=1)MAE: 2.07 -> 1.54Improved
add stochastic approximation updates for latent variables rather than the fixed-step SGLD-EM update (ablation)SGLD-EM · Linear regression simulation test set (v0=0.1, σ=1)MSE: 6.94 -> 4.42Improved
add adaptive latent-variable updates to SGLD (ablation)SGLD · Linear regression simulation test set (v0=0.1, σ=1)MAE: 7.72 -> 1.54Improved
add adaptive latent-variable updates to SGHMC (ablation)SGHMC on DA-MNIST · DA-MNISTaccuracy: 99.63 -> 99.75Improved
add adaptive latent-variable updates to SGHMC (ablation)SGHMC on DA-FMNIST · DA-FMNISTaccuracy: 94.29 -> 94.38Improved
add simulated annealing to SGHMC-SA compression (ablation)SGHMC-SA · CIFAR10 ResNet20 (90% sparsity)accuracy: 91.45 -> 91.68Improved
add adaptive stochastic approximation to annealed SGHMC compression (ablation)A-SGHMC · CIFAR10 ResNet20 (90% sparsity)accuracy: 90.59 -> 91.68Improved
add adaptive stochastic approximation to annealed SGHMC compression (ablation)A-SGHMC · CIFAR10 ResNet20 (30% sparsity)accuracy: 94.07 -> 94.23No clear effect
increase target sparsity from 30% to 90% (ablation)A-SGHMC-SA · CIFAR10 ResNet20accuracy: 94.23 -> 91.68Hurt
use SGHMC-SA instead of Vanilla or DropoutCNN · MNIST adversarial examples (ζ=0.5)accuracy: 11% higher than Vanilla and Dropout; 1% higher than SGHMCImproved

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