Research map / Optimization / Implicit bias and generalization
Understanding the role of importance weighting for deep learning
Da Xu, Yuting Ye, Chuanwei Ruan
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Select weights according to the inverse margin | Gradient descent with a linear classifier on separable data · Separable data | Convergence to the max-margin solution | Improved |
| Change the importance weights | Gradient descent with a linear classifier on non-separable data · Non-separable data | Final solution intercept | Mixed |
| Apply importance weighting | Gradient descent after asymptotic convergence on separable data · Separable data | Training margin | No clear effect |
| Apply importance weighting during finite-step optimization | Gradient descent · Finite-step optimization | Solution margin | Mixed |
Closest papers by meaning
- Optimizing importance weighting in the presence of sub-population shifts (ICLR 2025 · similarity 0.90)
- Why Do We Need Weight Decay in Modern Deep Learning? (NeurIPS 2024 · similarity 0.84)
- Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks (ICML 2024 · similarity 0.83)
- Variable Importance in High-Dimensional Settings Requires Grouping (AAAI 2024 · similarity 0.83)
- Simplicity Bias in Overparameterized Machine Learning (AAAI 2024 · similarity 0.83)
- Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks (NeurIPS 2025 · similarity 0.82)
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.
