AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization

Ondrej Bohdal, Yongxin Yang, Timothy Hospedales

NeurIPS 2021 · Architectures and efficiency › RNNs and normalization · approach: Scalable approximation and equivariant compute · 5 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
meta-learn rotation with EvoGradLeNet · MNIST rotated 30 degtest accuracy (%): 81.79 -> 98.11Improved
replace T1-T2 with EvoGrad in Meta-Weight-NetResNet-32 · CIFAR-10 40% noisetest accuracy (%): 87.54 -> 87.74Improved
replace T1-T2 with EvoGrad in Meta-Weight-NetResNet-32 · CIFAR-100 40% noisetest accuracy (%): 58.64 -> 57.44Hurt
replace T1-T2 with EvoGrad in Meta-Weight-NetResNet-32 · CIFAR-10 20% noisetest accuracy (%): 90.33 -> 89.86Hurt
replace T1-T2 with EvoGrad in Meta-Weight-NetResNet-32 · CIFAR-10 0% noisetest accuracy (%): 92.04 -> 92.02No clear effect
add Meta-Weight-Net reweighting under label noiseResNet-32 · CIFAR-100 40% noisetest accuracy (%): 43.01 -> 57.44Improved
add Meta-Weight-Net reweighting without label noiseResNet-32 · CIFAR-10 0% noisetest accuracy (%): 92.89 -> 92.02Hurt
replace T1-T2 with EvoGrad in MetaXLMetaXL · WikiAnn NERaverage F1 (%): 71.13 -> 71.98Improved
replace T1-T2 with EvoGrad in MetaXL (our run)MetaXL · WikiAnn NERaverage F1 (%): 69.59 -> 71.98Improved
replace T1-T2 with EvoGrad in LFTRelationNet ResNet10 · CUB 5-way 1-shotaccuracy (%): 48.38 -> 47.39Hurt
replace T1-T2 with EvoGrad in LFTRelationNet ResNet10 · Plantae 5-way 5-shotaccuracy (%): 50.39 -> 52.92Improved
scale feature extractor from ResNet10 to ResNet34 with EvoGradLFT RelationNet · Plantae 5-way 1-shotaccuracy (%): 36.00 -> 38.23Improved

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