Pith. sign in

REVIEW 6 cited by

Dynamic Model Pruning with Feedback

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2006.07253 v1 pith:BUPG5XYQ submitted 2020-06-12 cs.LG stat.ML

Tao Lin , Sebastian U. Stich , Luis Barba , Daniil Dmitriev , Martin Jaggi This is my paper
classification cs.LGstat.ML
keywords modelmodelsperformancesparsedynamicfeedbackmethodpruning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Deep neural networks often have millions of parameters. This can hinder their deployment to low-end devices, not only due to high memory requirements but also because of increased latency at inference. We propose a novel model compression method that generates a sparse trained model without additional overhead: by allowing (i) dynamic allocation of the sparsity pattern and (ii) incorporating feedback signal to reactivate prematurely pruned weights we obtain a performant sparse model in one single training pass (retraining is not needed, but can further improve the performance). We evaluate our method on CIFAR-10 and ImageNet, and show that the obtained sparse models can reach the state-of-the-art performance of dense models. Moreover, their performance surpasses that of models generated by all previously proposed pruning schemes.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training

    cs.LG 2025-10 conditional novelty 6.0 of 10

    CAGE, a curvature-aware correction that adds the quantization error to the gradient, reduces loss in low-bit quantization-aware training, letting 3-bit CAGE-trained models match 4-bit baseline-trained models.

  2. Hyperpruning: Efficient Search through Pruned Variants of Recurrent Neural Networks Leveraging Lyapunov Spectrum

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A Lyapunov-spectrum-based distance to the dense network lets hyperparameter search for pruned RNNs stop early and select models that beat both loss-based baselines and the dense originals.

  3. Compositional Zero-Shot Recognition based on Tangent Space Disentanglement for Composite Modulation Signals

    eess.SP 2026-07 reject novelty 4.0 of 10

    TSDN recognizes unseen combinations of inner and outer modulations by log-transforming composite signals and learning layer-specific classifiers, but the core linearization is derived for positive real signals while t...

  4. Delta-SVD: Efficient Compression for Personalized Text-to-Image Models

    cs.CV 2025-08 conditional novelty 4.0 of 10

    DreamBooth fine-tuning updates are low-rank, so post-hoc SVD with energy-based truncation compresses personalized models by up to 270x with mild quality loss.

  5. Resource-Efficient Automatic Software Vulnerability Assessment via Knowledge Distillation and Particle Swarm Optimization

    cs.LG 2025-07 conditional novelty 4.0 of 10

    A PSO-guided knowledge distillation framework compresses a CodeBERT vulnerability assessor to 0.6% of its original size while retaining 89.3% of its accuracy.

  6. Long-Tailed Data Classification by Increasing and Decreasing Neurons During Training

    cs.LG 2025-07 reject novelty 4.0 of 10

    A dynamic neuron replacement scheme, with gradients reweighted by class frequency, improves long-tailed image classification accuracy by 1-4% over fixed networks in the reported experiments.

Pith tools