Research map / Learning theory and algorithms / Kernels and regression theory
Memorization With Neural Nets: Going Beyond the Worst Case
Sjoerd Dirksen, Patrick Finke, Martin Genzel
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 |
|---|---|---|---|
| use a nonzero maximal bias lambda for the random hyperplanes in the first layer (ablation) | Three-layer interpolation algorithm · Two Moons | interpolation probability | Improved |
| increase first-layer width n when lambda exceeds the data radius | Three-layer interpolation algorithm · Two Moons | interpolation probability | Improved |
| use the proposed algorithm instead of one neuron per sample | Three-layer interpolation algorithm · Two Moons | second-layer width | Improved |
Closest papers by meaning
- Generalizablity of Memorization Neural Network (NeurIPS 2024 · similarity 0.89)
- The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets (NeurIPS 2025 · similarity 0.87)
- Unveiling Memorization–Generalization Coexistence: A Case Study on Arithmetic Tasks with Label Noise (NeurIPS 2026 · similarity 0.87)
- On the Optimal Memorization Capacity of Transformers (ICLR 2025 · similarity 0.86)
- IOFM: Using the Interpolation Technique on the Over-Fitted Models to Identify Clean-Annotated Samples (AAAI 2024 · similarity 0.86)
- Towards Memorization Estimation: Fast, Formal and Free (ICML 2025 · similarity 0.86)
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.
