VC-Dimension and Generalization in Geometric Machine Learning with Applications to Active Learning
stat.ML, cs.LG, math.DG
Submitted: 2026-11-09
Updated: 2026-11-09
Terminology
Sources
- Shortest path distance in random k-nearest neighbor graphs
- Neural Embeddings of Graphs in Hyperbolic Space
- Choosing the parameter of the Fermat distance: navigating geometry and noise
- The Vapnik-Chervonenkis dimension of cubes in $\mathbb{R}^d$
- On the Vapnik-Chervonenkis dimension of products of intervals in $\mathbb{R}^d$
- Power Weighted Shortest Paths for Clustering Euclidean Data
- Active Learning for Convolutional Neural Networks: A Core-Set Approach
- Poincar'e GloVe: Hyperbolic Word Embeddings
- Helfrich's Energy and Constrained Minimisation
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference