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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Federated Unlearning: How to Efficiently Erase a Client in FL?


Jul 12, 2022
Anisa Halimi, Swanand Kadhe, Ambrish Rawat, Nathalie Baracaldo

* Updatable ML (UpML) Workshop, International Conference on Machine Learning (ICML) 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Leveraging Spatial and Temporal Correlations in Sparsified Mean Estimation


Oct 14, 2021
Divyansh Jhunjhunwala, Ankur Mallick, Advait Gadhikar, Swanand Kadhe, Gauri Joshi

* Accepted to NeurIPS 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning


Sep 23, 2020
Swanand Kadhe, Nived Rajaraman, O. Ozan Koyluoglu, Kannan Ramchandran

* Shorter version accepted in ICML Workshop on Federated Learning, July 2020, and CCS Workshop on Privacy-Preserving Machine Learning in Practice, November 2020 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Communication-Efficient Gradient Coding for Straggler Mitigation in Distributed Learning


May 14, 2020
Swanand Kadhe, O. Ozan Koyluoglu, Kannan Ramchandran

* Shorter version accepted in 2020 IEEE International Symposium on Information Theory (ISIT) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Communication-Efficient and Byzantine-Robust Distributed Learning


Nov 21, 2019
Avishek Ghosh, Raj Kumar Maity, Swanand Kadhe, Arya Mazumdar, Kannan Ramchandran


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Gradient Coding Based on Block Designs for Mitigating Adversarial Stragglers


Apr 30, 2019
Swanand Kadhe, O. Ozan Koyluoglu, Kannan Ramchandran

* Shorter version accepted in 2019 IEEE International Symposium on Information Theory (ISIT) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

OverSketched Newton: Fast Convex Optimization for Serverless Systems


Mar 21, 2019
Vipul Gupta, Swanand Kadhe, Thomas Courtade, Michael W. Mahoney, Kannan Ramchandran

* 27 pages, 11 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email