AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Robust Differentiable SVD

Wei Wang, Zheng Dang, Yinlin Hu, Pascal Fua, Mathieu Salzmann

TPAMI 2021 · Architectures and efficiency › RNNs and normalization · approach: Weight normalization and decay interplay · 70 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 Taylor expansion instead of power iteration gradients in backward pass (ablation)SVD-PI · CIFAR10 ZCA (d=64)mean error (%): 4.59 -> 4.50Improved
use Taylor expansion instead of gradient clipping (ablation)SVD-Clip · CIFAR10 ZCA (d=64)mean error (%): 4.83 -> 4.50Improved
use Taylor gradients instead of plain SVD gradients (ablation)SVD · CIFAR10 ZCA (d=8)success rate: 0% -> 100%Improved
raise epsilon from 1e-4 to 1e-2 (K=19) (ablation)SVD-Taylor · CIFAR100 ZCA (d=64)success rate: 50% -> 87.5%Improved
lower Taylor degree K from 19 to 9 (ablation)SVD-Taylor · CIFAR100 ZCA (d=64)success rate: 87.5% -> 100%Improved
lower Taylor degree K from 19 to 9 (ablation)SVD-Taylor · CIFAR100 ZCA (d=64)mean error (%): 21.45 -> 21.14Improved
use larger matrix groups d=32 with Taylor instead of batch norm (ablation)ResNet50 · CIFAR100mean error (%): 21.62 -> 19.47Improved
use Taylor instead of SVD-PI (ablation)ResNet50 · CIFAR100 ZCA (d=4)mean error (%): 20.98 -> 20.34Improved
use Taylor instead of SVD-PI (ablation)ResNet18 · Tiny ImageNet val (d=64)mean error (%): 36.83 -> 36.72No clear effect
use Taylor instead of SVD-PI (ablation)AlexNet · ImageNet second-order poolingtop-1 error: not converged -> 38.74Improved
use SVD-WCT instead of GD-WCT regularized network (ablation)style transfer · Artworksmean classification accuracy: 64.71 -> 83.30Improved
use Taylor instead of gradient clipping in WCT (ablation)style transfer · Artworksmean classification accuracy: 60.27 -> 83.30Improved

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