# Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training

arXiv: https://arxiv.org/abs/2306.12230 · HTML: https://mlsanity.com/paper/2306.12230/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 66 references that are in the map.
- First posted on arXiv 21 Jun 2023.

## Builds on (most cited first, 30 of 53)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [A Simple and Effective Pruning Approach for Large Language Models](https://mlsanity.com/paper/2306.11695/) (2023)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks](https://mlsanity.com/paper/2102.00554/) (2021)
- [Rigging the Lottery: Making All Tickets Winners](https://mlsanity.com/paper/1911.11134/) (2019)
- [Pruning neural networks without any data by iteratively conserving synaptic flow](https://mlsanity.com/paper/2006.05467/) (2020)
- [The State of Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1902.09574/) (2019)
- [Picking Winning Tickets Before Training by Preserving Gradient Flow](https://mlsanity.com/paper/2002.07376/) (2020)
- [Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science](https://mlsanity.com/paper/1707.04780/) (2017)
- [A Survey of Model Compression and Acceleration for Deep Neural Networks](https://mlsanity.com/paper/1710.09282/) (2017)
- [What's Hidden in a Randomly Weighted Neural Network?](https://mlsanity.com/paper/1911.13299/) (2019)
- [Sparse Networks from Scratch: Faster Training without Losing Performance](https://mlsanity.com/paper/1907.04840/) (2019)
- [Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask](https://mlsanity.com/paper/1905.01067/) (2019)
- [Pruning Neural Networks at Initialization: Why are We Missing the Mark?](https://mlsanity.com/paper/2009.08576/) (2020)
- [Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch](https://mlsanity.com/paper/2102.04010/) (2021)
- [The Hardware Lottery](https://mlsanity.com/paper/2009.06489/) (2020)
- [Deep Rewiring: Training very sparse deep networks](https://mlsanity.com/paper/1711.05136/) (2017)
- [A Bayesian Perspective on Generalization and Stochastic Gradient Descent](https://mlsanity.com/paper/1710.06451/) (2017)

## Built on by (most cited first, 17 of 17)

- [Dynamic Sparse Training versus Dense Training: The Unexpected Winner in Image Corruption Robustness](https://mlsanity.com/paper/2410.03030/) (2024)
- [SCAN: Bootstrapping Contrastive Pre-training for Data Efficiency](https://mlsanity.com/paper/2411.09126/) (2024)
- [Accelerating Learnt Video Codecs with Gradient Decay and Layer-wise Distillation](https://mlsanity.com/paper/2312.02605/) (2023)
- [Navigating Extremes: Dynamic Sparsity in Large Output Spaces](https://mlsanity.com/paper/2411.03171/) (2024)
- [Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolution](https://mlsanity.com/paper/2505.24037/) (2025)
- [A Comparative Study of Pruning Methods in Transformer-based Time Series Forecasting](https://mlsanity.com/paper/2412.12883/) (2024)
- [Sparse-to-Sparse Training of Diffusion Models](https://mlsanity.com/paper/2504.21380/) (2025)
- [Mixed Sparsity Training: Achieving 4× FLOP Reduction for Transformer Pretraining](https://mlsanity.com/paper/2408.11746/) (2024)
- [EntryPrune: Neural Network Feature Selection using First Impressions](https://mlsanity.com/paper/2410.02344/) (2024)
- [NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling](https://mlsanity.com/paper/2505.17909/) (2025)
- [Addressing the Collaboration Dilemma in Low-Data Federated Learning via Transient Sparsity](https://mlsanity.com/paper/2506.00932/) (2025)
- [Neuro-inspired Ensemble-to-Ensemble Communication Primitives for Sparse and Efficient ANNs](https://mlsanity.com/paper/2508.14140/) (2025)
- [A Recovery Guarantee for Sparse Neural Networks](https://mlsanity.com/paper/2509.20323/) (2025)
- [Exploring the impact of adaptive rewiring in Graph Neural Networks](https://mlsanity.com/paper/2602.10754/) (2026)
- [Rethinking Reservoir Pruning: A Dynamical Perspective for Echo State Networks](https://mlsanity.com/paper/2608.04593/) (2026)
- [HAND: A Biologically-Inspired Activation Function that Improves Generalisation and Sample Efficiency in Image Classification](https://mlsanity.com/paper/2610.11534/) (2026)
- [When Sparsity Breaks Connectivity: Functional Reachability and Guided Topology Dynamics in Extreme Sparse Training](https://mlsanity.com/paper/2610.17425/) (2026)

## Abstract (arXiv)

Dynamic Sparse Training (DST) is a rapidly evolving area of research that seeks to optimize the sparse initialization of a neural network by adapting its topology during training. It has been shown that under specific conditions, DST is able to outperform dense models. The key components of this framework are the pruning and growing criteria, which are repeatedly applied during the training process to adjust the network's sparse connectivity. While the growing criterion's impact on DST performance is relatively well studied, the influence of the pruning criterion remains overlooked. To address this issue, we design and perform an extensive empirical analysis of various pruning criteria to better understand their impact on the dynamics of DST solutions. Surprisingly, we find that most of the studied methods yield similar results. The differences become more significant in the low-density regime, where the best performance is predominantly given by the simplest technique: magnitude-based pruning. The code is provided at https://github.com/alooow/fantastic_weights_paper