Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
SHUFFLESPARSE: Learned Shuffles for Structured Sparse Networks
Abhishek Tyagi, Arjun Iyer, Liam Young +3
Structured weight sparsity accelerates training and inference on modern GPUs, but it trails unstructured dynamic sparse training (DST) in accuracy especially at extreme sparsity. W…
cs.LG2025
Dynamic Sparse Training of Diagonally Sparse Networks
Abhishek Tyagi, Arjun Iyer, William H Renninger +2
Recent advances in Dynamic Sparse Training (DST) have pushed the frontier of sparse neural network training in structured and unstructured contexts, matching dense-model performanc…