Search Results for author:
Found 4 papers, 0 papers with code
Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data
Modern deep learning models are usually highly over-parameterized so that they can overfit the training data.
Per-Example Gradient Regularization Improves Learning Signals from Noisy Data
In this paper, we explore the per-example gradient regularization (PEGR) and present a theoretical analysis that demonstrates its effectiveness in improving both test error and robustness against noise perturbations.
Multiple Descent in the Multiple Random Feature Model
Recent works have demonstrated a double descent phenomenon in over-parameterized learning.
Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping
A main contribution from the paper is that we identify the difficulty of the classification problem as a driving factor for the appearance of heavy tail in weight matrices spectra.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
