Research map / Learning theory and algorithms / Sample complexity
CS4ML: A general framework for active learning with arbitrary data based on Christoffel functions
Juan M Cardenas, Ben Adcock, Nick Dexter
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 |
|---|---|---|---|
| sample with Christoffel-function-based measure (CS) instead of Monte Carlo sampling | gradient-augmented polynomial regression · exp(-(theta_1+...+theta_d)/(2d)), d=2,4,8, log-linear m | average regression error | Improved |
| sample frequency lines with CS instead of uniform random sampling | generative-model MRI reconstruction · 3D brain MRI, 0.125%, 0.375%, 0.625% sampling | PSNR | Improved |
| use Christoffel Adaptive Sampling (CAS) instead of Monte Carlo sampling | PINN for Burgers equation · tanh and sigmoid 5x50 DNNs | test error vs number of samples | Improved |
| use empirical approximation of the optimal sampling measure instead of exact sampling | CS for generative models · MRI reconstruction | PSNR | Improved |
| apply CS in cases outside the theory (nonlinear PDE operator, adaptive scheme) | CAS PINNs · Burgers equation | test error | Improved |
| use log-linear scaling of m with n for MCS | MCS gradient-augmented polynomial regression · hyperbolic cross polynomial spaces | generalization error | Hurt |
| apply CS in other settings | CS4ML · appendix cases | error | No clear effect |
Closest papers by meaning
- A Unified Framework for Learning with Nonlinear Model Classes from Arbitrary Linear Samples (ICML 2024 · similarity 0.86)
- On the Benefits of Active Data Collection in Operator Learning (ICML 2025 · similarity 0.86)
- Improved Active Learning via Dependent Leverage Score Sampling (ICLR 2024 · similarity 0.86)
- Transductive Active Learning: Theory and Applications (NeurIPS 2024 · similarity 0.85)
- Active Learning for Neural PDE Solvers (ICLR 2025 · similarity 0.84)
- Active Learning for Derivative-Based Global Sensitivity Analysis with Gaussian Processes (NeurIPS 2024 · similarity 0.84)
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.
