AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Blessing of Depth in Linear Regression: Deeper Models Have Flatter Landscape Around the True Solution

Jianhao Ma, Salar Fattahi

NeurIPS 2022 · Learning theory and algorithms › Matrix and tensor methods · approach: High-dimensional estimation theory · 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
replace cross-entropy with l1-lossResNet-18 · CIFAR-10 10% label noisetest accuracy: 91.52% -> 94.16%Improved
replace cross-entropy with l1-lossResNet-50 · CIFAR-10 10% label noisetest accuracy: 90.87% -> 92.68%Improved
replace cross-entropy with l1-lossResNet-18 · CIFAR-100 10% label noisetest accuracy: 70.17% -> 73.14%Improved
replace cross-entropy with l1-lossResNet-50 · CIFAR-100 10% label noisetest accuracy: 71.30% -> 76.46%Improved
increase depth from ResNet-18 to ResNet-50 with l1-lossResNet l1-loss · CIFAR-100 10% label noisetest accuracy: 73.14% -> 76.46%Improved
increase depth from ResNet-18 to ResNet-50 with l1-lossResNet l1-loss · CIFAR-10 10% label noisetest accuracy: 94.16% -> 92.68%Hurt
increase depth from ResNet-18 to ResNet-50 with CE lossResNet CE · CIFAR-10 10% label noisetest accuracy: 91.52% -> 90.87%No clear effect
use 4-layer instead of 2- or 3-layer modelSubGM on deep matrix recovery · synthetic, 5% corruptedgeneralization errorImproved
use 3-layer instead of 2-layer modelSubGM on diagonal linear regression · synthetic robust regressiongeneralization errorImproved
increase depth NSubGM on diagonal linear regression · synthetic robust regressionconvergence speedHurt
use 4-layer ReLU model with l1-lossSubGM · synthetic sin(theta^T x), 5% corruptedmodel-mismatch errorImproved

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