Research map / Learning theory and algorithms / Sample complexity
The Implications of Local Correlation on Learning Some Deep Functions
Eran Malach, Shai Shalev-Shwartz
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 |
|---|---|---|---|
| train a linear classifier on a single 3x3 patch instead of guessing randomly | linear classifier · CIFAR | test accuracy: 10 % -> 18.0-21.3 % | Improved |
| train a linear classifier on a single 3x3 patch instead of guessing randomly | linear classifier · ImageNet | top-1 test accuracy: 0.1% -> 0.25-0.46% | Improved |
| train a linear classifier on a single 3x3 patch instead of guessing randomly | linear classifier · ImageNet | top-5 test accuracy: 0.5% -> 1.2-1.5% | Improved |
| read out from higher layers and positions nearer the image center of ResNet-50 | linear readout from ResNet-50 features · ImageNet | top-5 accuracy | Improved |
Closest papers by meaning
- Theoretical Analysis of the Inductive Biases in Deep Convolutional Networks (NeurIPS 2023 · similarity 0.86)
- Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs (ICLR 2024 · similarity 0.85)
- From Linear to Nonlinear: Provable Weak-to-Strong Generalization through Feature Learning (NeurIPS 2025 · similarity 0.83)
- Asymptotics of Learning with Deep Structured (Random) Features (ICML 2024 · similarity 0.83)
- How Deep Networks Learn Sparse and Hierarchical Data: the Sparse Random Hierarchy Model (ICML 2024 · similarity 0.83)
- Position: A Theory of Deep Learning Must Include Compositional Sparsity (ICML 2025 · similarity 0.83)
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.
