AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron

Jingfeng Wu, Difan Zou, Zixiang Chen, Vladimir Braverman, Quanquan Gu, Sham M. Kakade

ICML 2023 · Optimization › Implicit bias and generalization · approach: Shallow ReLU network convergence · 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
Use GLM-tron instead of SGDReLU regression with symmetric Bernoulli data, well-specified setting · Well-specified ReLU regression, symmetric Bernoulliexpected excess risk: min_{\gamma^{\tron}_0<1/2} \Ebb \excessrisk(\wB_N^{\tron}) \lesssim min_{\gamma^{\sgd}_0<1}\Ebb \excessrisk(\wB_N^{\sgd}Improved
Use GLM-tron instead of SGDNoiseless ReLU regression with symmetric Bernoulli data · Noiseless ReLU regression, symmetric Bernoulliexpected population risk: \Ebb_{\wB_*} \Ebb_{\algo} \risk(\wB_N^{\tron}) \lesssim \big\| \wB_0 - \wB_* \big\|^2_{\prod_{t=1}^{N}\big( \IB-\frac{\gImproved
Apply GLM-tron in the well-specified setting under symmetric Bernoulli featuresGLM-tron · Well-specified ReLU regression, symmetric Bernoulliexpected excess risk: \Ebb \excessrisk (\wB_{N}) \lesssim \big\| \wB_0 - \wB_* \big\|^2_{\prod_{t=1}^{N}(\IB-\frac{\gamma_t}{2}\HB)\HB} + \sigImproved
Apply GLM-tron in the misspecified setting with hypercontractive featuresGLM-tron · Misspecified ReLU regressionexpected population risk: \Ebb \risk (\wB_{N}) \lesssim \OPT + \bigg\| \prod_{t=1}^{N}\Big(\IB-\frac{\gamma_t}{2}\HB\Big)(\wB_0 - \wB_*) \bigg\|^2Improved
Use GLM-tron's finite-dimensional bound rather than its prior \Ocal(\OPT + \sqrt{d/N}) boundGLM-tron · Misspecified ReLU regression, finite dimensionexpected population risk: \OPT + \frac{d}{\Neff} = \OPT + \frac{d\log(N)}{N}; prior bound: \Ocal(\OPT + \sqrt{d/N})Improved
Replace GLM-tron's update with the ReLU-derivative update used by SGDGLM-tron on noiseless ReLU regression with symmetric Bernoulli data · Noiseless ReLU regression, symmetric Bernoulliexpected population risk: \Ebb_{\wB_*} \Ebb_{\algo} \risk(\wB_N^{\sgd}) \ge \half \cdot \| \wB_*\|^2_{\HB}\ge \half \cdot \risk(0)Hurt

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