arXiv cs.AI / cs.LG / cs.CL·4d agoA Spectral Theory of Grokking: Weight Decay induces Feature Learning#grokking#feature-learning#ntkAI research
arXiv cs.AI / cs.LG / cs.CL·19d agoA Theoretical Analysis of Generalization Dynamics in Neural Networks under Gradient Descent with Weight Decay#generalization#gradient-descent#grokkingAI research