Model Compression & Optimization

Model compression has emerged as an important area of research for deploying deep learning models on IoT devices. However, model compression is not a sufficient solution to fit the models within the memory of a single device; as a result we need to distribute them across multiple devices. This leads to a distributed inference paradigm in which communication costs represent another major bottleneck. To this end, we focus on knowledge distillation and ‘teacher’ – ‘student’ type of architectures for distributed model compression, as well as data independent model compression.

model compressions

Selected Publications

8 entries « 1 of 2 »

Krishnakumar, Anish; Marculescu, Radu; Ogras, Umit Y

INDENT: Incremental Online Decision Tree Training for Domain-Specific Systems-on-Chip Inproceedings Forthcoming

In: 2022 IEEE/ACM International Conference On Computer Aided Design (ICCAD), Forthcoming.

BibTeX

Farcas, Allen-Jasmin; Chen, Xiaohan; Wang, Zhangyang; Marculescu, Radu

Model Elasticity for Hardware Heterogeneity in Federated Learning Systems Inproceedings Forthcoming

In: FedEdge 2022 - 1st ACM Workshop on Data Privacy and Federated Learning Technologies for Mobile Edge Network, Forthcoming.

BibTeX

Li, Guihong; Mandal, Sumit K; Ogras, Umit Y; Marculescu, Radu

FLASH: Fast Neural Architecture Search with Hardware Optimization Journal Article

In: ACM Transactions on Embedded Computing Systems, vol. 20, no. 63, pp. 1-26, 2021.

Links | BibTeX

Bhardwaj, K.; Li, G.; Marculescu, R.

How does topology influence gradient propagation and model performance of deep networks with DenseNet-type skip connections? Inproceedings

In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 13498-13507, 2021.

Links | BibTeX

Farcas, Allen-Jasmin; Li, Guihong; Bhardwaj, Kartikeya; Marculescu, Radu

A Hardware Prototype Targeting Distributed Deep Learning for On-Device Inference Inproceedings

In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 398–399, 2020.

Links | BibTeX

Bhardwaj, Kartikeya; Suda, Naveen; Marculescu, Radu

Dream distillation: A data-independent model compression framework Journal Article

In: arXiv preprint arXiv:1905.07072, 2019.

Links | BibTeX

8 entries « 1 of 2 »