Learning a Single Neuron with Gradient Methods

We consider the fundamental problem of learning a single neuron x (cid:55)→ σ(w(cid:62)x) in a realizable setting, using standard gradient methods with random initialization, and under general families of input distributions and activations.

Data and Resources

Cite this as

Gilad Yehudai, Ohad Shamir (2025). Dataset: Learning a Single Neuron with Gradient Methods. https://doi.org/10.57702/w2cjrx4t

DOI retrieved: January 2, 2025

Additional Info

Field Value
Created January 2, 2025
Last update January 2, 2025
Defined In https://doi.org/10.48550/arXiv.2001.05205
Author Gilad Yehudai
More Authors
Ohad Shamir