AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Simplicity Bias in 1-Hidden Layer Neural Networks

Depen Morwani, jatin batra, Prateek Jain, Praneeth Netrapalli

NeurIPS 2023 · Architectures and efficiency › RNNs and normalization · approach: Representation geometry and collapse · 1 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
Train a second model on features orthogonal to the first model's important directions (OrthoP), rather than training it independentlyResNet-50 feature-based 1-hidden-layer classifiers · B-Imagenette, Imagenette, Waterbirds, MNIST-CIFARMistake diversity: 3.87± 1.54 -> 21.15±1.57; 6.6±0.46 -> 11.44±0.65; 2.9±0.52 -> 14.53±0.48; 0.0±0.0 -> 5.56±7.89Improved
Train a second model on features orthogonal to the first model's important directions (OrthoP), rather than training it independentlyResNet-50 feature-based 1-hidden-layer classifiers · B-Imagenette, Imagenette, Waterbirds, MNIST-CIFARClass-conditioned logit correlation: 99.88±0.01 -> 90.86±1.08; 99.31±0.12 -> 91±0.59; 99.66±0.04 -> 93.81±0.48; 99.76±0.17 -> 78.74±2.28Improved
Use a low-dimensional projection to isolate the trained model's influential input directions1-hidden-layer FCNs in the rich regime · b-Imagenette, Imagenette, Waterbirds, MNIST-CIFARRandomized accuracy under P versus P_perp mixing: P_perp-RA: 89.94±0.22, 75.89±0.25, 91.47±0.11, 94.15±0.21; P-RA: 49.53±0.24, 9.33±0.01, 62.51±0.07, 55.2±0.13Mixed
Find a low-dimensional influential projection despite high-rank first-layer weights1-hidden-layer FCNs in the lazy regime · b-Imagenette, Imagenette, Waterbirds, MNIST-CIFARRandomized accuracy under P versus P_perp mixing: P_perp-RA: 90.07±0.34, 68.25±1.18, 89.67±0.42, 99.45±0.17; P-RA: 52.09±1.34, 11.92±0.82, 62.44±4.48, 49.83±0.67Mixed
Train the second ensemble model on P_perp-projected features and average its logits with the first modelOrthoP ensemble · Binary-Imagenette, Imagenette, Waterbirds-Landbirds under Gaussian noiseTest accuracyImproved

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