AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Revealing the Structure of Deep Neural Networks via Convex Duality

Tolga Ergen, Mert Pilanci

ICML 2021 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 13 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 closed-form optimal weights instead of SGD trainingDeep ReLU networks · Whitened MNIST and CIFAR-10training objectiveImproved
Use closed-form optimal weights instead of SGD trainingDeep ReLU networks · Whitened MNIST and CIFAR-10test errorImproved
Use closed-form optimal weights instead of full-batch SGDTwo-layer ReLU network with batch normalization · CIFAR-100training objectiveImproved
Use closed-form optimal weights instead of full-batch SGDTwo-layer ReLU network with batch normalization · CIFAR-100test accuracyImproved
Add batch normalization between layersDeep ReLU networks · Arbitrary dataweight alignment characterizationImproved
Use one-dimensional rank-one dataRegularized deep ReLU networks · One-dimensional interpolationspline interpolationImproved
Use whitened inputs and one-hot labelsDeep ReLU networks · Whitened dataavailability of closed-form optimal weightsImproved

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