2 papers
cs.NE2026
Pruning as Evolution: Emergent Sparsity Through Selection Dynamics in Neural Networks
Zubair Shah, Noaman Khan
Neural networks are commonly trained in highly overparameterized regimes, yet empirical evidence consistently shows that many parameters become redundant during learning. Most exis…
cs.AI2025
Pruning as a Game: Equilibrium-Driven Sparsification of Neural Networks
Zubair Shah, Noaman Khan
Neural network pruning is widely used to reduce model size and computational cost. Yet, most existing methods treat sparsity as an externally imposed constraint, enforced through h…