1.3k citations · 2.1k across the 35 of their papers we have counts for
11 papers · 1 filter
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…
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…
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…
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,…
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…
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…
On the Predictability of Pruning Across Scales
Jonathan S. Rosenfeld, Jonathan Frankle, Michael Carbin +1
We show that the error of iteratively magnitude-pruned networks empirically follows a scaling law with interpretable coefficients that depend on the architecture and task. We funct…
Comparing Rewinding and Fine-tuning in Neural Network Pruning
Alex Renda, Jonathan Frankle, Michael Carbin
Many neural network pruning algorithms proceed in three steps: train the network to completion, remove unwanted structure to compress the network, and retrain the remaining structu…
Linear Mode Connectivity and the Lottery Ticket Hypothesis
Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy +1
We study whether a neural network optimizes to the same, linearly connected minimum under different samples of SGD noise (e.g., random data order and augmentation). We find that st…
Stabilizing the Lottery Ticket Hypothesis
Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M. Roy +1
Pruning is a well-established technique for removing unnecessary structure from neural networks after training to improve the performance of inference. Several recent results have…
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Jonathan Frankle, Michael Carbin
Neural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of infere…