AI Paper Atlas

Research map / Optimization / Optimizers

Low Bias Low Variance Gradient Estimates for Boolean Stochastic Networks

Adeel Pervez, Taco Cohen, Efstratios Gavves

ICML 2020 · Optimization › Optimizers · approach: Stochastic gradient MCMC · 3 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
Importance reweighting of Straight-Through gradient by 0.5/p(z_i) (FouST) instead of plain STBoolean stochastic networks (FouST) · OMNIGLOT stochastic MLPs (one and two layers)training ELBOImproved
Fourier noise operator (rho=0.5, correlated samples) applied to decoder, versus independent samples (ablation)FouST on stochastic ResNet VAE · CIFAR-10training ELBO (bits/dimension)Improved
Fourier noise operator applied to decoder (vs. no NoiseOp) (ablation)FouST on stochastic ResNet VAE with 64-channel layer · CIFAR-10training stabilityImproved
Decrease noise operator rho (more stable training) (ablation)FouST with Fourier noise operator · CIFAR-10training stabilityImproved
Wider 256-channel stochastic layer with noise operator, single layer (vs 4-layer FouST)FouST · CIFAR-10validation bits per dimension: 4.16 -> 4.02 bpdImproved
Replace unbiased REBAR with FouST (biased, single decoder evaluation)two-layer stochastic MLP on MNIST · MNIST test ELBOtest ELBO: -94.43 vs -91.94Improved
Uniform-sampling/discounting Taylor terms and representation rescaling tau for FouSTBoolean stochastic networks · toy problem minimizing E[(z-t)^2]convergence to optimal p(z=+1)=0Improved

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