Kartikeya Bhardwaj

According to our database, Kartikeya Bhardwaj authored at least 33 papers between 2013 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Oh! We Freeze: Improving Quantized Knowledge Distillation via Signal Propagation Analysis for Large Language Models.

Kartikeya Bhardwaj, Nilesh Prasad Pandey, Sweta Priyadarshi, Kyunggeun Lee, Jun Ma, Harris Teague

CoRR, 2024

2023

Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunities.

Guihong Li, Duc Hoang, Kartikeya Bhardwaj, Ming Lin, Zhangyang Wang, Radu Marculescu

CoRR, 2023

TIPS: Topologically Important Path Sampling for Anytime Neural Networks.

Guihong Li, Kartikeya Bhardwaj, Yuedong Yang, Radu Marculescu

Proceedings of the International Conference on Machine Learning, 2023

ZiCo: Zero-shot NAS via inverse Coefficient of Variation on Gradients.

Guihong Li, Yuedong Yang, Kartikeya Bhardwaj, Radu Marculescu

Proceedings of the Eleventh International Conference on Learning Representations, 2023

ZiCo-BC: A Bias Corrected Zero-Shot NAS for Vision Tasks.

Kartikeya Bhardwaj, Hsin-Pai Cheng, Sweta Priyadarshi, Zhuojin Li

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022

Restructurable Activation Networks.

Kartikeya Bhardwaj, James Ward, Caleb Tung, Dibakar Gope, Lingchuan Meng, Igor Fedorov, Alex Chalfin, Paul N. Whatmough, Danny Loh

CoRR, 2022

Collapsible Linear Blocks for Super-Efficient Super Resolution.

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

Proceedings of Machine Learning and Systems 2022, 2022

Super-Efficient Super Resolution for Fast Adversarial Defense at the Edge.

Kartikeya Bhardwaj, Dibakar Gope, James Ward, Paul N. Whatmough, Danny Loh

Proceedings of the 2022 Design, Automation & Test in Europe Conference & Exhibition, 2022

2021

EdgeAl: A Vision for Deep Learning in the IoT Era.

Kartikeya Bhardwaj, Naveen Suda, Radu Marculescu

IEEE Des. Test, 2021

How Does Topology Influence Gradient Propagation and Model Performance of Deep Networks With DenseNet-Type Skip Connections?

Kartikeya Bhardwaj, Guihong Li, Radu Marculescu

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

2020

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

Kartikeya Bhardwaj, Wei Chen, Radu Marculescu

CoRR, 2020

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

Wei Chen, Kartikeya Bhardwaj, Radu Marculescu

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2020

On Network Science and Mutual Information for Explaining Deep Neural Networks.

Brian Davis, Umang Bhatt, Kartikeya Bhardwaj, Radu Marculescu, José M. F. Moura

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

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

Kartikeya Bhardwaj, Wei Chen, Radu Marculescu

Proceedings of the 57th ACM/IEEE Design Automation Conference, 2020

A Hardware Prototype Targeting Distributed Deep Learning for On-device Inference.

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

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019

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

Kartikeya Bhardwaj, Chingyi Lin, Anderson L. Sartor, Radu Marculescu

ACM Trans. Embed. Comput. Syst., 2019

EdgeAI: A Vision for Deep Learning in IoT Era.

Kartikeya Bhardwaj, Naveen Suda, Radu Marculescu

CoRR, 2019

Towards Unifying Neural Architecture Space Exploration and Generalization.

Kartikeya Bhardwaj, Radu Marculescu

CoRR, 2019

Dream Distillation: A Data-Independent Model Compression Framework.

Kartikeya Bhardwaj, Naveen Suda, Radu Marculescu

CoRR, 2019

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

Brian Davis, Umang Bhatt, Kartikeya Bhardwaj, Radu Marculescu, José M. F. Moura

CoRR, 2019

2018

Climate Anomalies vs Air Pollution: Carbon Emissions and Anomaly Networks.

Anshul Goyal, Kartikeya Bhardwaj, Radu Marculescu

CoRR, 2018

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

Jiqian Dong, Gopaljee Atulya, Kartikeya Bhardwaj, Radu Marculescu

CoRR, 2018

Dimensionality Reduction via Community Detection in Small Sample Datasets.

Kartikeya Bhardwaj, Radu Marculescu

Proceedings of the Advances in Knowledge Discovery and Data Mining, 2018

2017

Non-Stationary Bayesian Learning for Global Sustainability.

Kartikeya Bhardwaj, Radu Marculescu

IEEE Trans. Sustain. Comput., 2017

Towards cell-based therapeutics: A bio-inspired autonomous drug delivery system.

Chieh Lo, Kartikeya Bhardwaj, Radu Marculescu

Nano Commun. Networks, 2017

Discovering Hidden Knowledge in Carbon Emissions Data: A Multilayer Network Approach.

Kartikeya Bhardwaj, HingOn Miu, Radu Marculescu

Proceedings of the Discovery Science - 20th International Conference, 2017

Enhancing precipitation models by capturing multivariate and multiscale climate dynamics.

Ruizhou Ding, Dimitrios Stamoulis, Kartikeya Bhardwaj, Diana Marculescu, Radu Marculescu

Proceedings of the 3rd International Workshop on Cyber-Physical Systems for Smart Water Networks, 2017

K-hop learning: a network-based feature extraction for improved river flow prediction.

Kartikeya Bhardwaj, Radu Marculescu

Proceedings of the 3rd International Workshop on Cyber-Physical Systems for Smart Water Networks, 2017

2016

An Autonomous and Adaptive Bacteria-based Drug Delivery System.

Chieh Lo, Kartikeya Bhardwaj, Radu Marculescu

Proceedings of the 3rd ACM International Conference on Nanoscale Computing and Communication, 2016

2014

C3Map and ARPSO based mapping algorithms for energy-efficient regular 3-D NoC architectures.

Kartikeya Bhardwaj, Pravin S. Mane

Proceedings of the Technical Papers of 2014 International Symposium on VLSI Design, 2014

Power- and area-efficient Approximate Wallace Tree Multiplier for error-resilient systems.

Kartikeya Bhardwaj, Pravin S. Mane, Jörg Henkel

Proceedings of the Fifteenth International Symposium on Quality Electronic Design, 2014

2013

K-Algorithm: An Improved Booth's Recoding for Optimal Fault-Tolerant Reversible Multiplier.

Kartikeya Bhardwaj, Bharat M. Deshpande

Proceedings of the 26th International Conference on VLSI Design and 12th International Conference on Embedded Systems, 2013

ACMA: Accuracy-configurable multiplier architecture for error-resilient System-on-Chip.

Kartikeya Bhardwaj, Pravin S. Mane

Proceedings of the 2013 8th International Workshop on Reconfigurable and Communication-Centric Systems-on-Chip (ReCoSoC), 2013