2 papers
cs.LG2026
When Sparsity Breaks Connectivity: Functional Reachability and Guided Topology Dynamics in Extreme Sparse Training
Mohammad Pasande, Mateusz Jaworski, Jeroen Rook +1
Dynamic Sparse Training (DST) periodically prunes and regrows connections, inducing a discrete dynamical mechanism over network topologies. At extreme sparsity (), this d…
cs.LG2026
Beyond Masked Sparsity: SNACK Enables Truly Sparse Neural Networks on GPU
Jafar Badour, Maurice van Keulen, Elena Mocanu
Deep neural networks continue to grow in parameter count, driving up training and inference cost on GPUs. Sparse neural networks and Dynamic Sparse Training (DST) promise to reduce…