3 papers
cs.AI2026
SHARP: Sleep-based Hierarchical Accelerated Replay for Long Range Non-Stationary Temporal Pattern Recognition
Jayanta Dey, Shikhar Srivastava, Itamar Lerner +2
Learning long-range non-stationary temporal patterns remains a core challenge for modern sequence models, particularly in strict streaming settings. In these settings, data arrive…
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…