Publication

What can linearized neural networks actually say about generalization?

Related publications (38)

About
Privacy
Disclaimer

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

What can linearized neural networks actually say about generalization?

Graph Chatbot

Chat with Graph Search

Machine Learning for Modeling Stock Returns

Benign Overfitting in Deep Neural Networks under Lazy Training

Bayes-optimal Learning of Deep Random Networks of Extensive-width

From Kernel Methods to Neural Networks: A Unifying Variational Formulation

Deep Learning Generalization with Limited and Noisy Labels

Penalising the biases in norm regularisation enforces sparsity

A new variable shape parameter strategy for RBF approximation using neural networks

Privacy-preserving federated neural network training and inference

Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study

Sharp asymptotics on the compression of two-layer neural networks