Saurav Prakash

According to our database, Saurav Prakash authored at least 22 papers between 2019 and 2024.

Collaborative distances:

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

2024

Embracing Federated Learning: Enabling Weak Client Participation via Partial Model Training.

Sunwoo Lee, Tuo Zhang, Saurav Prakash, Yue Niu, Salman Avestimehr

IEEE Trans. Mob. Comput., December, 2024

Federated Classification in Hyperbolic Spaces via Secure Aggregation of Convex Hulls.

Saurav Prakash, Jin Sima, Chao Pan, Eli Chien, Olgica Milenkovic

Trans. Mach. Learn. Res., 2024

ATP: Enabling Fast LLM Serving via Attention on Top Principal Keys.

Yue Niu, Saurav Prakash, Salman Avestimehr

CoRR, 2024

All Rivers Run to the Sea: Private Learning with Asymmetric Flows.

Yue Niu, Ramy E. Ali, Saurav Prakash, Salman Avestimehr

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

Overcoming Resource Constraints in Federated Learning: Large Models Can Be Trained with only Weak Clients.

Yue Niu, Saurav Prakash, Souvik Kundu, Sunwoo Lee, Salman Avestimehr

Trans. Mach. Learn. Res., 2023

Revisiting Sparsity Hunting in Federated Learning: Why does Sparsity Consensus Matter?

Sara Babakniya, Souvik Kundu, Saurav Prakash, Yue Niu, Salman Avestimehr

Trans. Mach. Learn. Res., 2023

Machine Unlearning of Federated Clusters.

Chao Pan, Jin Sima, Saurav Prakash, Vishal Rana, Olgica Milenkovic

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

CodedReduce: A Fast and Robust Framework for Gradient Aggregation in Distributed Learning.

Amirhossein Reisizadeh, Saurav Prakash, Ramtin Pedarsani, Amir Salman Avestimehr

IEEE/ACM Trans. Netw., 2022

Basil: A Fast and Byzantine-Resilient Approach for Decentralized Training.

Ahmed Roushdy Elkordy, Saurav Prakash, Salman Avestimehr

IEEE J. Sel. Areas Commun., 2022

Federated Learning of Large Models at the Edge via Principal Sub-Model Training.

Yue Niu, Saurav Prakash, Souvik Kundu, Sunwoo Lee, Salman Avestimehr

CoRR, 2022

Federated Sparse Training: Lottery Aware Model Compression for Resource Constrained Edge.

Sara Babakniya, Souvik Kundu, Saurav Prakash, Yue Niu, Salman Avestimehr

CoRR, 2022

2021

Coded Computing for Low-Latency Federated Learning Over Wireless Edge Networks.

Saurav Prakash, Sagar Dhakal, Mustafa Riza Akdeniz, Yair Yona, Shilpa Talwar, Salman Avestimehr, Nageen Himayat

IEEE J. Sel. Areas Commun., 2021

2020

Coded Computing for Distributed Graph Analytics.

Saurav Prakash, Amirhossein Reisizadeh, Ramtin Pedarsani, Amir Salman Avestimehr

IEEE Trans. Inf. Theory, 2020

Mitigating Byzantine Attacks in Federated Learning.

Saurav Prakash, Amir Salman Avestimehr

CoRR, 2020

Coded Computing for Federated Learning at the Edge.

Saurav Prakash, Sagar Dhakal, Mustafa Riza Akdeniz, Amir Salman Avestimehr, Nageen Himayat

CoRR, 2020

Hierarchical Coded Gradient Aggregation for Learning at the Edge.

Saurav Prakash, Amirhossein Reisizadeh, Ramtin Pedarsani, Amir Salman Avestimehr

Proceedings of the IEEE International Symposium on Information Theory, 2020

2019

Coded Computation Over Heterogeneous Clusters.

Amirhossein Reisizadeh, Saurav Prakash, Ramtin Pedarsani, Amir Salman Avestimehr

IEEE Trans. Inf. Theory, 2019

A Pre-defined Sparse Kernel Based Convolution for Deep CNNs.

Souvik Kundu, Saurav Prakash, Haleh Akrami, Peter A. Beerel, Keith M. Chugg

CoRR, 2019

Coded Computing for Distributed Machine Learning in Wireless Edge Network.

Sagar Dhakal, Saurav Prakash, Yair Yona, Shilpa Talwar, Nageen Himayat

Proceedings of the 90th IEEE Vehicular Technology Conference, 2019

Tree Gradient Coding.

Amirhossein Reisizadeh, Saurav Prakash, Ramtin Pedarsani, Amir Salman Avestimehr

Proceedings of the IEEE International Symposium on Information Theory, 2019

Coded Federated Learning.

Sagar Dhakal, Saurav Prakash, Yair Yona, Shilpa Talwar, Nageen Himayat

Proceedings of the 2019 IEEE Globecom Workshops, Waikoloa, HI, USA, December 9-13, 2019, 2019

pSConv: A Pre-defined S parse Kernel Based Convolution for Deep CNNs.

Souvik Kundu, Saurav Prakash, Haleh Akrami, Peter A. Beerel, Keith M. Chugg

Proceedings of the 57th Annual Allerton Conference on Communication, 2019