AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Empirical Phase Diagram for Three-layer Neural Networks with Infinite Width

Hanxu Zhou, Qixu Zhou, Zhenyuan Jin, Tao Luo, Yaoyu Zhang, Zhi-Qin John Xu

NeurIPS 2022 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 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
Vary initialization scaling while keeping (γ2, γ3) fixedThree-layer ReLU NN · Synthetic 4-point dataset, Group 1 (γ2=0, γ3=1.1)S_W1 and S_W2: $S_{\vW_1}$: $-0.4108$, $-0.4084$, $-0.4231$; $S_{\vW_2}$: $-0.9119$, $-0.9364$, $-0.9310$No clear effect
Vary initialization scaling while keeping (γ2, γ3) fixedThree-layer ReLU NN · Synthetic 4-point dataset, Group 2 (γ2=0.7, γ3=2.5)S_W1 and S_W2: $S_{\vW_1}$: $-0.3130$, $-0.3176$, $-0.3243$; $S_{\vW_2}$: $0.0251$, $0.0263$, $0.0205$No clear effect
Increase γ3 across initialization regimesThree-layer ReLU NN, first hidden layer · Synthetic 4-point datasetRelative change of input weightsMixed
Move into the condensed regimeThree-layer ReLU NN, hidden-layer input weights · Synthetic 4-point dataset and MNISTRelative change of input weightsMixed
Use different dynamical regimes for different hidden layersThree-layer ReLU NN · Synthetic 4-point dataset and MNISTLayerwise dynamical regimeImproved
Enter the condensed regime, where active input weights concentrate in isolated orientationsThree-layer ReLU NN · Synthetic 4-point datasetWeight-orientation condensationImproved

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