On Generalization in Bilevel Least Squares with Overparameterized Neural Networks
stat.ML, cs.LG
Submitted: 2026-11-07
Updated: 2026-11-07
Code: https://github.com/fareselkhoury/OBO
Terminology
Sources
- Towards a Unified Analysis of Neural Networks in Nonparametric Instrumental Variable Regression: Optimization and Generalization
- Parametric Rates for Nonparametric Conditional-Moment Bilevel Optimization
- Approximation Methods for Bilevel Programming
- On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization
- Gaussian Error Linear Units (GELUs)
- Generalization Ability of Wide Neural Networks on $\mathbb{R}$
- Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
- Searching for Activation Functions
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