Minimax Rates and Spectral Distillation for Tree Ensembles
stat.ML, cs.AI, cs.LG
Submitted: 2026-05-12
Updated: 2026-11-10
Terminology
Sources
- The Random Forest Kernel and other kernels for big data from random partitions
- Distilling a Neural Network Into a Soft Decision Tree
- Distilling the Knowledge in a Neural Network
- Spectral Inference Networks: Unifying Deep and Spectral Learning
- Operator SVD with Neural Networks via Nested Low-Rank Approximation
- Interpreting Models via Single Tree Approximation
- Minimax rates for learning kernels in operators
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