1 citations · 1 across the 6 of their papers we have counts for
8 papers
Learn Your Own Thoughts: Abstract Token Curriculum
Khashayar Gatmiry, Avrajit Ghosh, Parsa Mirtaheri +4
Large Language Models (LLMs) have achieved remarkable reasoning capabilities by utilizing chain-of-thought (CoT) as a scratchpad for intermediate stages of thinking. However, CoT t…
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…
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 Hes…
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…
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…
Optimal Eye Surgeon: Finding Image Priors through Sparse Generators at Initialization
Avrajit Ghosh, Xitong Zhang, Kenneth K. Sun +3
We introduce Optimal Eye Surgeon (OES), a framework for pruning and training deep image generator networks. Typically, untrained deep convolutional networks, which include image sa…
Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness
Guangliang Liu, Milad Afshari, Xitong Zhang +5
While task-agnostic debiasing provides notable generalizability and reduced reliance on downstream data, its impact on language modeling ability and the risk of relearning social b…