# ERDE: Entropy-Regularized Distillation for Early-exit

arXiv: https://arxiv.org/abs/2510.04856 · HTML: https://mlsanity.com/paper/2510.04856/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Early exit and edge inference, one of 12 directions in Efficient LLM inference and serving.
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 6 Oct 2025.

## Placed in

- Efficient LLM inference and serving / [Early exit and edge inference](https://mlsanity.com/inference/early-exit-and-edge-inference/)
- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 15 of 15)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Adaptive Computation Time for Recurrent Neural Networks](https://mlsanity.com/paper/1603.08983/) (2016)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [Learning Factored Representations in a Deep Mixture of Experts](https://mlsanity.com/paper/1312.4314/) (2013)
- [Learning to Stop While Learning to Predict](https://mlsanity.com/paper/2006.05082/) (2020)
- [Predictive Exit: Prediction of Fine-Grained Early Exits for Computation- and Energy-Efficient Inference](https://mlsanity.com/paper/2206.04685/) (2022)
- [Energy-efficient Amortized Inference with Cascaded Deep Classifiers](https://mlsanity.com/paper/1710.03368/) (2017)
- [Fair Multi-Exit Framework for Facial Attribute Classification](https://mlsanity.com/paper/2301.02989/) (2023)

## Abstract (arXiv)

Although deep neural networks and in particular Convolutional Neural Networks have demonstrated state-of-the-art performance in image classification with relatively high efficiency, they still exhibit high computational costs, often rendering them impractical for real-time and edge applications. Therefore, a multitude of compression techniques have been developed to reduce these costs while maintaining accuracy. In addition, dynamic architectures have been introduced to modulate the level of compression at execution time, which is a desirable property in many resource-limited application scenarios. The proposed method effectively integrates two well-established optimization techniques: early exits and knowledge distillation, where a reduced student early-exit model is trained from a more complex teacher early-exit model. The primary contribution of this research lies in the approach for training the student early-exit model. In comparison to the conventional Knowledge Distillation loss, our approach incorporates a new entropy-based loss for images where the teacher's classification was incorrect. The proposed method optimizes the trade-off between accuracy and efficiency, thereby achieving significant reductions in computational complexity without compromising classification performance. The validity of this approach is substantiated by experimental results on image classification datasets CIFAR10, CIFAR100 and SVHN, which further opens new research perspectives for Knowledge Distillation in other contexts.