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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Accuracy Boosters: Epoch-Driven Mixed-Mantissa Block Floating-Point for DNN Training


Nov 22, 2022
Simla Burcu Harma, Canberk Sönmez, Babak Falsafi, Martin Jaggi, Yunho Oh


   Access Paper or Ask Questions

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

Scalable Collaborative Learning via Representation Sharing


Nov 20, 2022
Frédéric Berdoz, Abhishek Singh, Martin Jaggi, Ramesh Raskar


   Access Paper or Ask Questions

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

Modular Clinical Decision Support Networks (MoDN) -- Updatable, Interpretable, and Portable Predictions for Evolving Clinical Environments


Nov 12, 2022
Cécile Trottet, Thijs Vogels, Martin Jaggi, Mary-Anne Hartley

* Extended Abstract presented at Machine Learning for Health (ML4H) symposium 2022, November 28th, 2022, New Orleans, United States & Virtual, http://www.ml4h.cc, 9 pages 

   Access Paper or Ask Questions

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

FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings


Oct 10, 2022
Jean Ogier du Terrail, Samy-Safwan Ayed, Edwige Cyffers, Felix Grimberg, Chaoyang He, Regis Loeb, Paul Mangold, Tanguy Marchand, Othmane Marfoq, Erum Mushtaq, Boris Muzellec, Constantin Philippenko, Santiago Silva, Maria Teleńczuk, Shadi Albarqouni, Salman Avestimehr, Aurélien Bellet, Aymeric Dieuleveut, Martin Jaggi, Sai Praneeth Karimireddy, Marco Lorenzi, Giovanni Neglia, Marc Tommasi, Mathieu Andreux

* Accepted to NeurIPS, Datasets and Benchmarks Track 

   Access Paper or Ask Questions

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

Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning


Jun 16, 2022
Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi


   Access Paper or Ask Questions

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

Beyond spectral gap: The role of the topology in decentralized learning


Jun 07, 2022
Thijs Vogels, Hadrien Hendrikx, Martin Jaggi

* Under review 

   Access Paper or Ask Questions

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

On Avoiding Local Minima Using Gradient Descent With Large Learning Rates


May 30, 2022
Amirkeivan Mohtashami, Martin Jaggi, Sebastian Stich


   Access Paper or Ask Questions

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

SKILL: Structured Knowledge Infusion for Large Language Models


May 17, 2022
Fedor Moiseev, Zhe Dong, Enrique Alfonseca, Martin Jaggi

* NAACL 2022 

   Access Paper or Ask Questions

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

Data-heterogeneity-aware Mixing for Decentralized Learning


Apr 13, 2022
Yatin Dandi, Anastasia Koloskova, Martin Jaggi, Sebastian U. Stich


   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
5
6
7
>>