AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation

Sahil Singla, Eric Wallace, Shi Feng, Soheil Feizi

ICML 2019 · Optimization › Implicit bias and generalization · approach: Edge-of-stability dynamics · 24 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
Add the Hessian term to first-order interpretation (ablation)CAFO on ImageNet ILSVRC-2012 with ResNet-50 · ImageNet ILSVRC-2012 validation, high-confidence predictionsinterpretation similarityNo clear effect
Add the Hessian term to first-order interpretation (ablation)CAFO on ImageNet ILSVRC-2012 with ResNet-50 · ImageNet ILSVRC-2012 validation, low-confidence predictionsinterpretation differenceMixed
Use group-feature sparsity regularization instead of isolated feature importance (ablation)CAFO and CASO · ImageNet ILSVRC-2012visual coherenceImproved
Use group-feature sparsity regularization instead of isolated feature importance (ablation)CAFO and CASO · ImageNet ILSVRC-2012saliency-map noiseImproved
Use ordinary gradient descent rather than proximal gradient descent with the L1 penalty (ablation)CAFO and CASO with positive L1 regularization · ImageNet interpretation optimizationconvergence qualityHurt
Increase the L1 regularization parameter until the interpretation becomes all zeros (ablation)CAFO and CASO · ImageNet ILSVRC-2012saliency-map sparsityMixed
Multiply importance values by raw input pixels (ablation)saliency-map visualization methods · Image interpretationvisual artifactsHurt

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