2 papers
cs.AI2026
Loss-Aware Feature-Map Pruning in Convolutional Neural Networks Using Multi-Armed Bandits
Salem Ameen, Sunil Vadera
Convolutional neural networks often contain redundant feature maps that increase storage and inference cost. This paper presents a loss-aware feature-map pruning framework using mu…
cs.LG2026
Structured Neuron Pruning in Deep Neural Networks Using Multi-Armed Bandits
Salem Ameen, Sunil Vadera
Deep neural networks often contain redundant hidden units. Removing individual weights can reduce parameter count, but unstructured sparsity is not always easy to exploit in standa…