SelectPFN advances Bayesian variable selection for sparse nonlinear regression

Researchers have developed SelectPFN, a novel Prior-Data Fitted Network (PFN) capable of performing Bayesian variable selection and prediction simultaneously for sparse nonlinear regression. This new model can identify which input variables are most influential for its predictions in a single forward pass, offering posterior inclusion probabilities. SelectPFN demonstrates improved performance over existing methods like lasso and BART on various datasets, particularly in detecting interaction-only variables. AI

IMPACT This research could improve the interpretability and efficiency of models used in sparse nonlinear regression tasks.

RANK_REASON The cluster contains a research paper detailing a new method for sparse nonlinear regression. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Bart
• Bayesian Variable Selection in Linear Regression
• Dart
• group-penalized sparse neural network
• group spike-and-slab sparse-input neural network
• lasso
• LassoNet: Deep Lasso-Selection of 3D Point Clouds
• Prior-Data Fitted Networks
• SelectPFN
• sparse nonlinear regression

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →