Search Results for author:
Found 3 papers, 0 papers with code
How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers
We prove that such a random NN interpolator typically generalizes well if there exists an underlying narrow ``teacher NN" that agrees with the labels.
Continual Learning in Linear Classification on Separable Data
We analyze continual learning on a sequence of separable linear classification tasks with binary labels.
Reconstructing Training Data from Multiclass Neural Networks
Reconstructing samples from the training set of trained neural networks is a major privacy concern.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
