# In defense of parameter sharing for model-compression

arXiv: https://arxiv.org/abs/2310.11611 · HTML: https://mlsanity.com/paper/2310.11611/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 26 references that are in the map.
- First posted on arXiv 17 Oct 2023.

## Builds on (most cited first, 20 of 20)

- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (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)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (2018)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Linear Mode Connectivity and the Lottery Ticket Hypothesis](https://mlsanity.com/paper/1912.05671/) (2019)
- [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)
- [Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science](https://mlsanity.com/paper/1707.04780/) (2017)
- [Speeding up Convolutional Neural Networks with Low Rank Expansions](https://mlsanity.com/paper/1405.3866/) (2014)
- [Tensorizing Neural Networks](https://mlsanity.com/paper/1509.06569/) (2015)
- [Pruning Neural Networks at Initialization: Why are We Missing the Mark?](https://mlsanity.com/paper/2009.08576/) (2020)
- [Compressing Neural Networks with the Hashing Trick](https://mlsanity.com/paper/1504.04788/) (2015)
- [Deep Rewiring: Training very sparse deep networks](https://mlsanity.com/paper/1711.05136/) (2017)
- [SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems](https://mlsanity.com/paper/1903.03129/) (2019)
- [Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients](https://mlsanity.com/paper/2202.08132/) (2022)
- [Deep Expander Networks: Efficient Deep Networks from Graph Theory](https://mlsanity.com/paper/1711.08757/) (2017)
- [Scalable and Sustainable Deep Learning via Randomized Hashing](https://mlsanity.com/paper/1602.08194/) (2016)
- [Semantically Constrained Memory Allocation (SCMA) for Embedding in Efficient Recommendation Systems](https://mlsanity.com/paper/2103.06124/) (2021)

## Built on by (most cited first, 5 of 5)

- [Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation](https://mlsanity.com/paper/2410.06364/) (2024)
- [Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression](https://mlsanity.com/paper/2603.18426/) (2026)
- [Changing Base Without Losing Pace: A GPU-Efficient Alternative to MatMul in DNNs](https://mlsanity.com/paper/2503.12211/) (2025)
- [Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling](https://mlsanity.com/paper/2604.21724/) (2026)
- [Meta-Sparsity: Learning Optimal Sparse Structures in Multi-task Networks through Meta-learning](https://mlsanity.com/paper/2501.12115/) (2025)

## Abstract (arXiv)

When considering a model architecture, there are several ways to reduce its memory footprint. Historically, popular approaches included selecting smaller architectures and creating sparse networks through pruning. More recently, randomized parameter-sharing (RPS) methods have gained traction for model compression at start of training. In this paper, we comprehensively assess the trade-off between memory and accuracy across RPS, pruning techniques, and building smaller models. Our findings demonstrate that RPS, which is both data and model-agnostic, consistently outperforms/matches smaller models and all moderately informed pruning strategies, such as MAG, SNIP, SYNFLOW, and GRASP, across the entire compression range. This advantage becomes particularly pronounced in higher compression scenarios. Notably, even when compared to highly informed pruning techniques like Lottery Ticket Rewinding (LTR), RPS exhibits superior performance in high compression settings. This points out inherent capacity advantage that RPS enjoys over sparse models. Theoretically, we establish RPS as a superior technique in terms of memory-efficient representation when compared to pruning for linear models. This paper argues in favor of paradigm shift towards RPS based models. During our rigorous evaluation of RPS, we identified issues in the state-of-the-art RPS technique ROAST, specifically regarding stability (ROAST's sensitivity to initialization hyperparameters, often leading to divergence) and Pareto-continuity (ROAST's inability to recover the accuracy of the original model at zero compression). We provably address both of these issues. We refer to the modified RPS, which incorporates our improvements, as STABLE-RPS.