Research map / Learning theory and algorithms / Kernels and regression theory
Adaptive Approximation and Generalization of Deep Neural Network with Intrinsic Dimensionality
Ryumei Nakada, Masaaki Imaizumi
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 |
|---|---|---|---|
| decrease intrinsic dimension d of covariates (4,16 vs 64,100) in synthetic data with D=128 (ablation) | DNN · synthetic regression D=128 | generalization error | Improved |
| use DNN instead of k-NN and NW kernel estimators on non-smooth support (D=5, d=2 and d=4) | k-NN and NW kernel · synthetic regression on union of l1/2 and l2 balls | generalization error | Improved |
| increase added Gaussian-noise dimension d from 0 to 100 in MNIST (ablation) | DNN · MNIST contaminated | estimated convergence rate: -0.20 -> -0.16 | Hurt |
Closest papers by meaning
- The Intrinsic Dimension of Images and Its Impact on Learning (ICLR 2021 · similarity 0.88)
- On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension (JMLR 2025 · similarity 0.88)
- Intrinsic dimension of data representations in deep neural networks (NeurIPS 2019 · similarity 0.88)
- Minimax Optimal Deep Neural Network Classifiers Under Smooth Decision Boundary (JMLR 2025 · similarity 0.88)
- The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images (ICLR 2024 · similarity 0.87)
- Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon (NeurIPS 2025 · similarity 0.87)
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.
