5 papers
Hard labels sampled from sparse targets mislead rotation invariant algorithms
Avrajit Ghosh, Bin Yu, Manfred Warmuth +1
One of the most common machine learning setups is logistic regression. In many classification models, including neural networks, the final prediction is obtained by applying a logi…
Understanding Untrained Deep Models for Inverse Problems: Algorithms and Theory
Ismail Alkhouri, Evan Bell, Avrajit Ghosh +3
In recent years, deep learning methods have been extensively developed for inverse imaging problems (IIPs), encompassing supervised, self-supervised, and generative approaches. Mos…
Variational Learning Finds Flatter Solutions at the Edge of Stability
Avrajit Ghosh, Bai Cong, Rio Yokota +5
Variational Learning (VL) has recently gained popularity for training deep neural networks. Part of its empirical success can be explained by theories such as PAC-Bayes bounds, min…
Learning Dynamics of Deep Linear Networks Beyond the Edge of Stability
Avrajit Ghosh, Soo Min Kwon, Rongrong Wang +2
Deep neural networks trained using gradient descent with a fixed learning rate often operate in the regime of "edge of stability" (EOS), where the largest eigenvalue of the He…
Pruning Unrolled Networks (PUN) at Initialization for MRI Reconstruction Improves Generalization
Shijun Liang, Evan Bell, Avrajit Ghosh +1
Deep learning methods are highly effective for many image reconstruction tasks. However, the performance of supervised learned models can degrade when applied to distinct experimen…