# ELSA: Partial Weight Freezing for Overhead-Free Sparse Network Deployment

arXiv: https://arxiv.org/abs/2312.06872 · HTML: https://mlsanity.com/paper/2312.06872/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 11 Dec 2023.

## Builds on (most cited first, 25 of 25)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [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)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks](https://mlsanity.com/paper/2102.00554/) (2021)
- [ResNet strikes back: An improved training procedure in timm](https://mlsanity.com/paper/2110.00476/) (2021)
- [ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks](https://mlsanity.com/paper/2102.11600/) (2021)
- [Only Train Once: A One-Shot Neural Network Training And Pruning Framework](https://mlsanity.com/paper/2107.07467/) (2021)
- [AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks](https://mlsanity.com/paper/2106.12379/) (2021)
- [Learning Best Combination for Efficient N:M Sparsity](https://mlsanity.com/paper/2206.06662/) (2022)
- [Effective Model Sparsification by Scheduled Grow-and-Prune Methods](https://mlsanity.com/paper/2106.09857/) (2021)
- [A Comparison of Optimization Algorithms for Deep Learning](https://mlsanity.com/paper/2007.14166/) (2020)
- [Compression-aware Training of Neural Networks using Frank-Wolfe](https://mlsanity.com/paper/2205.11921/) (2022)
- [FreezeNet: Full Performance by Reduced Storage Costs](https://mlsanity.com/paper/2011.14087/) (2020)
- [Is Complexity Required for Neural Network Pruning? A Case Study on Global Magnitude Pruning](https://mlsanity.com/paper/2209.14624/) (2022)
- [JaxPruner: A concise library for sparsity research](https://mlsanity.com/paper/2304.14082/) (2023)
- [CrAM: A Compression-Aware Minimizer](https://mlsanity.com/paper/2207.14200/) (2022)
- [Adaptive Compression-based Lifelong Learning](https://mlsanity.com/paper/1907.09695/) (2019)

## Abstract (arXiv)

We present ELSA, a practical solution for creating deep networks that can easily be deployed at different levels of sparsity. The core idea is to embed one or more sparse networks within a single dense network as a proper subset of the weights. At prediction time, any sparse model can be extracted effortlessly simply be zeroing out weights according to a predefined mask. ELSA is simple, powerful and highly flexible. It can use essentially any existing technique for network sparsification and network training. In particular, it does not restrict the loss function, architecture or the optimization technique. Our experiments show that ELSA's advantages of flexible deployment comes with no or just a negligible reduction in prediction quality compared to the standard way of using multiple sparse networks that are trained and stored independently.