Search Results for author:
Found 3 papers, 1 papers with code
The lazy (NTK) and rich ($μ$P) regimes: a gentle tutorial
A central theme of the modern machine learning paradigm is that larger neural networks achieve better performance on a variety of metrics.
More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory
In our era of enormous neural networks, empirical progress has been driven by the philosophy that more is better.
The Eigenlearning Framework: A Conservation Law Perspective on Kernel Regression and Wide Neural Networks
We derive simple closed-form estimates for the test risk and other generalization metrics of kernel ridge regression (KRR).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
