# Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression

arXiv: https://arxiv.org/abs/2505.18166 · HTML: https://mlsanity.com/paper/2505.18166/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 13 May 2025.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [Empirical Analysis of the Hessian of Over-Parametrized Neural Networks](https://mlsanity.com/paper/1706.04454/) (2017)
- [Self-Distillation Amplifies Regularization in Hilbert Space](https://mlsanity.com/paper/2002.05715/) (2020)
- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation](https://mlsanity.com/paper/2105.08919/) (2021)
- [Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks](https://mlsanity.com/paper/1710.11029/) (2017)
- [LLM Pruning and Distillation in Practice: The Minitron Approach](https://mlsanity.com/paper/2408.11796/) (2024)
- [A Survey on Uncertainty Quantification Methods for Deep Learning](https://mlsanity.com/paper/2302.13425/) (2023)
- [Self-Data Distillation for Recovering Quality in Pruned Large Language Models](https://mlsanity.com/paper/2410.09982/) (2024)
- [EPSD: Early Pruning with Self-Distillation for Efficient Model Compression](https://mlsanity.com/paper/2402.00084/) (2024)
- [On Accelerating Edge AI: Optimizing Resource-Constrained Environments](https://mlsanity.com/paper/2501.15014/) (2025)

## Abstract (arXiv)

Modern foundational models are often compressed via a combination of structured pruning and re-training to meet the strict compute, memory, and connectivity constraints of edge deployments. While state-of-the-art pruning schemes target the entire Transformer, we adopt a simple, layer-wise L2-norm pruning on only the MLP blocks as a fixed baseline. Our focus is not on achieving maximal compression, but on isolating the impact of the re-training loss function: (i) Fine-tuning with Cross- Entropy (L2PFT), which requires labeled data, versus (ii) Self-Distillation with KL-divergence, which leverages only teacher logits (no labels) (L2PSD). We evaluate both pipelines on the OLMo2- 7B-SFT model for CommonsenseQA suitable for intermittent or denied connectivity scenarios typical of edge networks. Under identical pruning schedules, KL-based distillation matches or exceeds CE fine-tuning in test accuracy, demonstrating that, even with a basic MLP-only pruning, the choice of loss function materially affects compressed model recovery in resource-constrained environments.