Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Kartikeya Bhardwaj

Collapsible Linear Blocks for Super-Efficient Super Resolution


Mar 17, 2021
Kartikeya Bhardwaj, Milos Milosavljevic, Alex Chalfin, Naveen Suda, Liam O'Neil, Dibakar Gope, Lingchuan Meng, Ramon Matas, Danny Loh


  Access Paper or Ask Questions

New Directions in Distributed Deep Learning: Bringing the Network at Forefront of IoT Design


Aug 25, 2020
Kartikeya Bhardwaj, Wei Chen, Radu Marculescu

* This preprint is for personal use only. The official article will appear in proceedings of Design Automation Conference (DAC), 2020. This work was presented at the DAC 2020 special session on Edge-to-Cloud Neural Networks for Machine Learning Applications in Future IoT Systems 

  Access Paper or Ask Questions

FedMAX: Mitigating Activation Divergence for Accurate and Communication-Efficient Federated Learning


Apr 07, 2020
Wei Chen, Kartikeya Bhardwaj, Radu Marculescu


  Access Paper or Ask Questions

EdgeAI: A Vision for Deep Learning in IoT Era


Oct 23, 2019
Kartikeya Bhardwaj, Naveen Suda, Radu Marculescu

* To appear in IEEE Design and Test 

  Access Paper or Ask Questions

Towards Unifying Neural Architecture Space Exploration and Generalization


Oct 02, 2019
Kartikeya Bhardwaj, Radu Marculescu


  Access Paper or Ask Questions

Memory- and Communication-Aware Model Compression for Distributed Deep Learning Inference on IoT


Jul 26, 2019
Kartikeya Bhardwaj, Chingyi Lin, Anderson Sartor, Radu Marculescu

* This preprint is for personal use only. The official article will appear as part of the ESWEEK-TECS special issue and will be presented in the International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS), 2019 

  Access Paper or Ask Questions

Dream Distillation: A Data-Independent Model Compression Framework


May 17, 2019
Kartikeya Bhardwaj, Naveen Suda, Radu Marculescu

* Presented at the ICML 2019 Joint Workshop on On-Device Machine Learning & Compact Deep Neural Network Representations (ODML-CDNNR) 

  Access Paper or Ask Questions

NIF: A Framework for Quantifying Neural Information Flow in Deep Networks


Jan 20, 2019
Brian Davis, Umang Bhatt, Kartikeya Bhardwaj, Radu Marculescu, Jose Moura

* In AAAI-19 Workshop on Network Interpretability for Deep Learning 

  Access Paper or Ask Questions

A Dynamic Network and Representation LearningApproach for Quantifying Economic Growth fromSatellite Imagery


Dec 01, 2018
Jiqian Dong, Gopaljee Atulya, Kartikeya Bhardwaj, Radu Marculescu

* Presented at NIPS 2018 Workshop on Machine Learning for the Developing World 

  Access Paper or Ask Questions