FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning

arXiv:2403.07094v1 Announce Type: new
Abstract: The increasing computational demands of modern neural networks present deployment challenges on resource-constrained devices. Network pruning offers a solution to reduce model size and computational cost while maintaining performance. However, most current pruning methods focus primarily on improving sparsity by reducing the number of nonzero parameters, often neglecting other deployment costs such as inference time, which are closely related to the number of floating-point operations (FLOPs). In this paper, we propose FALCON, a novel combinatorial-optimization-based …

abstract arxiv challenges computational cost cs.lg current deployment devices falcon focus however modern network networks neural network neural networks optimization parameters performance pruning reduce solution sparsity type