AI Paper Atlas

Research map / Optimization / Optimizers

Randomized Automatic Differentiation

Deniz Oktay, Nick McGreivy, Joshua Aduol, Alex Beatson, Ryan P Adams

ICLR 2021 · Optimization › Optimizers · approach: Randomized gradient estimation · 10 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
Use activation sampling with a large mini-batch instead of matching memory by reducing batch sizeRAD feedforward networks · CIFAR-10 and MNISTtraining loss convergenceImproved
Use activation sampling with a large mini-batch instead of reducing batch sizeRAD · Sequential-MNISTtraining loss convergenceNo clear effect
Sample different activations for each mini-batch element rather than reusing the same sample (ablation)RAD fully connected network · MNISTtraining loss convergenceImproved
Sample different activations for each mini-batch element rather than reusing the same sample (ablation)RAD convolutional network · CIFAR-10training loss convergenceNo clear effect
Use a random projection instead of activation sampling (ablation)RAD · MNIST and CIFAR-10training performanceNo clear effect
Use an activation fraction of 0.1 instead of the full graph (ablation)RAD · ConvNet trainingpeak memory (MBytes): 23.08 -> 3.28Improved
Use an activation fraction of 0.1 instead of the full graph (ablation)RAD · MNIST fully connected trainingpeak memory (MBytes): 2.69 -> 1.80Improved
Use an activation fraction of 0.1 instead of the full graph (ablation)RAD · Sequential-MNIST RNN trainingpeak memory (MBytes): 47.93 -> 7.01Improved
Randomize intermediate Jacobians without tailoring sampling to the graph structureRAD neural networks · Deep neural networksoptimization convergenceHurt
Apply RAD to selected gradient factors in the PDE estimatorReaction-diffusion PDE optimization · Linear reaction-diffusion PDEmemory reduction: 99%Improved

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