AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

The staircase property: How hierarchical structure can guide deep learning

Emmanuel Abbe, Enric Boix-Adserà, Matthew Stewart Brennan, Guy Bresler, Dheeraj Mysore Nagaraj

NeurIPS 2021 · Optimization › Implicit bias and generalization · approach: Neural tangent kernel analysis · 0 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
target the staircase function S_k instead of the single monomial chi_{1:k}ResNet with SGD · Boolean hypercube n=30, k=10training error / Fourier coefficient recoveryImproved
target the staircase function instead of the parity monomial under unbiased Rademacher dataResNet with SGD · n=30, k=10, m=6x10^4training error / Fourier coefficient recoveryImproved
target the staircase function instead of the monomial under Gaussian dataResNet with SGD · n=100, k=5, m=3x10^5training error / Fourier coefficient recoveryImproved
target the staircase function instead of the monomial under biased product distribution p=0.75ResNet with SGD · n=30, k=7, m=6x10^4training error / Fourier coefficient recoveryImproved
learn the double staircase function S_{7,7}ResNet with SGD · n=30, k=l=7, m=10^5training error / Fourier coefficient recoveryImproved
use ReLU ResNet with SGD instead of the theoretical quadratic-activation layerwise trainingResNet with SGD · Boolean hypercube staircase functionstraining error / Fourier coefficient recoveryImproved

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