Pith. sign in

On gradient regularizers for mmd gans.Advances in neural information processing systems, 31, 2018

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Smooth Model Compression without Fine-Tuning

cs.LG · 2025-05-30 · conditional · novelty 5.0

Training a ResNet-18 with smoothness penalties on weights, then compressing via truncated SVD, keeps 91% CIFAR-10 accuracy at 70% sparsity with no post-compression fine-tuning.

citing papers explorer

Showing 1 of 1 citing paper.

  • Smooth Model Compression without Fine-Tuning cs.LG · 2025-05-30 · conditional · none · ref 3

    Training a ResNet-18 with smoothness penalties on weights, then compressing via truncated SVD, keeps 91% CIFAR-10 accuracy at 70% sparsity with no post-compression fine-tuning.