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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent


Oct 13, 2022
Satyen Kale, Jason D. Lee, Chris De Sa, Ayush Sekhari, Karthik Sridharan

Add code


   Access Paper or Ask Questions

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

Private Matrix Approximation and Geometry of Unitary Orbits


Jul 06, 2022
Oren Mangoubi, Yikai Wu, Satyen Kale, Abhradeep Guha Thakurta, Nisheeth K. Vishnoi

Add code

* Proceedings of Thirty Fifth Conference on Learning Theory (COLT), PMLR 178:3547-3588, 2022 

   Access Paper or Ask Questions

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

Beyond Uniform Lipschitz Condition in Differentially Private Optimization


Jun 21, 2022
Rudrajit Das, Satyen Kale, Zheng Xu, Tong Zhang, Sujay Sanghavi

Add code


   Access Paper or Ask Questions

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

On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data


Jun 09, 2022
Jianyu Wang, Rudrajit Das, Gauri Joshi, Satyen Kale, Zheng Xu, Tong Zhang

Add code


   Access Paper or Ask Questions

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

Self-Consistency of the Fokker-Planck Equation


Jun 02, 2022
Zebang Shen, Zhenfu Wang, Satyen Kale, Alejandro Ribeiro, Aim Karbasi, Hamed Hassani

Add code

* Accepted to COLT 2022. The code can be found at https://github.com/shenzebang/self-consistency-jax 

   Access Paper or Ask Questions

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

Mixed Federated Learning: Joint Decentralized and Centralized Learning


May 26, 2022
Sean Augenstein, Andrew Hard, Lin Ning, Karan Singhal, Satyen Kale, Kurt Partridge, Rajiv Mathews

Add code

* 36 pages, 12 figures 

   Access Paper or Ask Questions

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

Reproducibility in Optimization: Theoretical Framework and Limits


Feb 09, 2022
Kwangjun Ahn, Prateek Jain, Ziwei Ji, Satyen Kale, Praneeth Netrapalli, Gil I. Shamir

Add code

* 51 pages 

   Access Paper or Ask Questions

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

Pushing the Efficiency-Regret Pareto Frontier for Online Learning of Portfolios and Quantum States


Feb 06, 2022
Julian Zimmert, Naman Agarwal, Satyen Kale

Add code


   Access Paper or Ask Questions

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

Agnostic Learnability of Halfspaces via Logistic Loss


Jan 31, 2022
Ziwei Ji, Kwangjun Ahn, Pranjal Awasthi, Satyen Kale, Stefani Karp

Add code


   Access Paper or Ask Questions

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

Efficient Methods for Online Multiclass Logistic Regression


Oct 10, 2021
Naman Agarwal, Satyen Kale, Julian Zimmert

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
>>