AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Tunable Sensitivity to Large Errors in Neural Network Training

Gil Keren, Sivan Sabato, Björn Schuller

AAAI 2017 · Optimization › Implicit bias and generalization · approach: Stability-based generalization analysis · 9 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 a smaller k (0.125–0.5) rather than k=1 in single-layer networksSingle-layer feed-forward networks · MNIST, SVHN, CIFAR-10, and CIFAR-100test error: 1.76% -> 1.74%; 16.88% -> 16.16%; 48.32% -> 47.06%; 75.18% -> 74.41%Improved
Use k=2 instead of k=13-layer network · SVHN, 400 units, momentum 0.5test error: 16.52% -> 16.52%No clear effect
Use k=2 instead of k=13-layer network · CIFAR-10, 400 units, momentum 0.5test error: 46.81% -> 46.63%Improved
Use k=0.5 instead of k=15-layer network · MNIST, 400 units, momentum 0.5test error: 1.71% -> 1.69%Improved
Use k=4 instead of k=15-layer network · SVHN, 400 units, momentum 0.5test error: 17.41% -> 16.49%Improved
Use k=4 instead of k=15-layer network · CIFAR-10, 800 units, momentum 0.5test error: 44.21% -> 44.24%Hurt
Use k=4 instead of k=15-layer network · CIFAR-100, 800 units, momentum 0.9test error: 74.32% -> 74.62%Hurt
Reduce sensitivity to large prediction errors using k=0.0625One-input, two-class synthetic classifier · Synthetic toy classificationtest error: 4.90% -> 3.61%Improved
Reduce k from 1 to 0.0625One-input, two-class synthetic classifier · Synthetic toy classificationtest cross-entropy loss: 0.288 -> 1.190Hurt
Select k by cross-validation rather than fixing it at 1Feed-forward networks across the reported benchmarks · MNIST, SVHN, CIFAR-10, and CIFAR-100test 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