3 papers
stat.ML2025
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…
cs.LG2024
BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference
Changwoo Lee, Soo Min Kwon, Qing Qu +1
Large-scale foundation models have demonstrated exceptional performance in language and vision tasks. However, the numerous dense matrix-vector operations involved in these large n…
cs.LG2023
Topology-enhanced machine learning for speech signal processing
Pingyao Feng, Siheng Yi, Haiyu Zhang +4
In artificial-intelligence-aided signal processing, existing deep learning models often exhibit a black-box structure. Here, conceptually beyond spectral analysis, we demonstrate t…