activity
20182022
most citedComparing Rewinding and Fine-tuning in Neural Network Pruning

180 citations · 259 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG20225 cited

Pruning's Effect on Generalization Through the Lens of Training and Regularization

Tian Jin, Michael Carbin, Daniel M. Roy +2

Practitioners frequently observe that pruning improves model generalization. A long-standing hypothesis based on bias-variance trade-off attributes this generalization improvement…

cs.LG20222 cited

Cello: Efficient Computer Systems Optimization with Predictive Early Termination and Censored Regression

Yi Ding, Alex Renda, Ahsan Pervaiz +2

Sample-efficient machine learning (SEML) has been widely applied to find optimal latency and power tradeoffs for configurable computer systems. Instead of randomly sampling from th…

cs.LG202031 cited

The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models

Tianlong Chen, Jonathan Frankle, Shiyu Chang +4

The computer vision world has been re-gaining enthusiasm in various pre-trained models, including both classical ImageNet supervised pre-training and recently emerged self-supervis…

cs.LG2020

DiffTune: Optimizing CPU Simulator Parameters with Learned Differentiable Surrogates

Alex Renda, Yishen Chen, Charith Mendis +1

CPU simulators are useful tools for modeling CPU execution behavior. However, they suffer from inaccuracies due to the cost and complexity of setting their fine-grained parameters,…

cs.LG2020

Pruning Neural Networks at Initialization: Why are We Missing the Mark?

Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy +1

Recent work has explored the possibility of pruning neural networks at initialization. We assess proposals for doing so: SNIP (Lee et al., 2019), GraSP (Wang et al., 2020), SynFlow…

cs.LG2020

The Lottery Ticket Hypothesis for Pre-trained BERT Networks

Tianlong Chen, Jonathan Frankle, Shiyu Chang +4

In natural language processing (NLP), enormous pre-trained models like BERT have become the standard starting point for training on a range of downstream tasks, and similar trends…