AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Understanding Square Loss in Training Overparametrized Neural Network Classifiers

Tianyang Hu, Jun Wang, Wenjia Wang, Zhenguo Li

NeurIPS 2022 · Learning theory and algorithms › Kernels and regression theory · approach: Generalization theory of deep networks · 4 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 square loss and simplex codingResNet-18 · CIFAR-10 testclean accuracy (%): 95.15 (0.11) -> 95.04 (0.07)No clear effect
Replace cross-entropy with square loss and simplex codingWRN-16-10 · CIFAR-10 testclean accuracy (%): 93.94 (0.16) -> 95.02 (0.11)Improved
Replace cross-entropy with square loss and simplex codingResNet-50 · CIFAR-100 testclean accuracy (%): 79.82 (0.14) -> 78.91 (0.14)Hurt
Replace cross-entropy with square loss and simplex codingWRN-16-10 · CIFAR-100 testclean accuracy (%): 77.89 (0.21) -> 79.65 (0.15)Improved
Replace cross-entropy with square loss and simplex codingResNet-18 · CIFAR-10 test, PGD-100, 2/255accuracy (%): 8.81 (1.61) -> 30.53 (0.92)Improved
Replace cross-entropy with square loss and simplex codingWRN-16-10 · CIFAR-10 test, PGD-100, 2/255accuracy (%): 1.04 (0.10) -> 37.47 (0.61)Improved
Replace cross-entropy with square loss and simplex codingResNet-50 · CIFAR-100 test, PGD-100, 2/255accuracy (%): 2.31 (0.07) -> 13.76 (1.30)Improved
Replace cross-entropy with square loss and simplex codingWRN-16-10 · CIFAR-100 test, PGD-100, 2/255accuracy (%): 0.83 (0.07) -> 6.48 (0.40)Improved
Replace cross-entropy with square loss and simplex codingResNet-18 · CIFAR-10 test, AutoAttack, 2/255accuracy (%): 2.74 (0.09) -> 4.10 (0.50)Improved
Replace cross-entropy with square loss and simplex codingWRN-16-10 · CIFAR-10 test, AutoAttack, 2/255accuracy (%): 0.33 (0.06) -> 5.37 (0.50)Improved
Replace cross-entropy with square loss and simplex codingResNet-50 · CIFAR-100 test, AutoAttack, 2/255accuracy (%): 0.99 (0.10) -> 3.67 (0.60)Improved
Replace cross-entropy with square loss and simplex codingWRN-16-10 · CIFAR-100 test, AutoAttack, 2/255accuracy (%): 0.42 (0.07) -> 2.73 (0.20)Improved

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