MLPrune: Multi-Layer Pruning for Automated Neural Network Compression

By Wenyuan Zeng, Raquel Urtasun. 2018

50 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Efficiency & Compression

Citations in the corpus

WoodFisher: Efficient Second-Order Approximation for Neural Network Compression (2020, methodology): “[20, 22, 33], usually set in the classical OBD/OBS framework [8, 10]; (2) iterative methods, e.”
WoodFisher: Efficient second-order approximations for model compression (2020, unknown): “, 2019), pruning (Zeng and Urtasun, 2019; Wang et al., 2019), reinforcementlearning (Wu et al.”
M-FAC: Efficient Matrix-Free Approximations of Second-Order Information (2021, methodology): “The Appendix contains full hyper-parameters, ablations with respect to block size and number of gradients, and a comparison with K-FAC pruning in a simpler setting [49].”
Effective Sparsification of Neural Networks with Global Sparsity Constraint (2021, unknown): “Network Pruning [10, 8, 39, 21, 24, 14, 41, 17, 34, 30, 38] has been extensively studied in recent years to reduce the model size and improve the inference efﬁciency of deep neural networks.”
EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis (2019, methodology): “Without much loss in accuracy, classification networks can be compressed by a factor of 10 or even more (Han et al., 2015b; Zeng & Urtasun, 2019) on ImageNet (Deng et al., 2009).”
Pruning neural networks without any data by iteratively conserving synaptic flow (2020, background): “Both SNIP and GraSP have been thoroughly benchmarked by [14] against other state-of-the-art pruning algorithms that involve training [2, 35, 10, 11, 36, 21, 20], demonstrating competitive performance.”
Picking Winning Tickets Before Training by Preserving Gradient Flow (2020, methodology): “Network pruning (LeCun et al., 1990; Hassibi et al., 1993; Han et al., 2015b; Dong et al., 2017; Zeng & Urtasun, 2019; Wang et al., 2019) has been shown to reduce the test-time resource requirements with minimal performance degradation.”