Projected Neural Additive Models as Universal Approximators
cs.LG
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/nhonphan7/pnam
Terminology
Sources
- NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning
- All elementary functions from a single binary operator
- Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients
- Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl
- Symbolic Regression is NP-hard
- Gaussian Error Linear Units (GELUs)
- Adam: A Method for Stochastic Optimization
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis