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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Scaling Deep Networks with the Mesh Adaptive Direct Search algorithm


Jan 17, 2023
Dounia Lakhmiri, Mahdi Zolnouri, Vahid Partovi Nia, Christophe Tribes, Sébastien Le Digabel

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 Convergence of Stochastic Gradient Descent in Low-precision Number Formats


Jan 09, 2023
Matteo Cacciola, Antonio Frangioni, Masoud Asgharian, Alireza Ghaffari, Vahid Partovi Nia

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

EuclidNets: An Alternative Operation for Efficient Inference of Deep Learning Models


Dec 22, 2022
Xinlin Li, Mariana Parazeres, Adam Oberman, Alireza Ghaffari, Masoud Asgharian, Vahid Partovi Nia

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

Training Integer-Only Deep Recurrent Neural Networks


Dec 22, 2022
Vahid Partovi Nia, Eyyüb Sari, Vanessa Courville, Masoud Asgharian

Add code

* arXiv admin note: substantial text overlap with arXiv:2109.09828 

   Access Paper or Ask Questions

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

KronA: Parameter Efficient Tuning with Kronecker Adapter


Dec 20, 2022
Ali Edalati, Marzieh Tahaei, Ivan Kobyzev, Vahid Partovi Nia, James J. Clark, Mehdi Rezagholizadeh

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

SeKron: A Decomposition Method Supporting Many Factorization Structures


Oct 12, 2022
Marawan Gamal Abdel Hameed, Ali Mosleh, Marzieh S. Tahaei, Vahid Partovi Nia

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

Integer Fine-tuning of Transformer-based Models


Sep 20, 2022
Mohammadreza Tayaranian, Alireza Ghaffari, Marzieh S. Tahaei, Mehdi Rezagholizadeh, Masoud Asgharian, Vahid Partovi Nia

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

DenseShift: Towards Accurate and Transferable Low-Bit Shift Network


Aug 20, 2022
Xinlin Li, Bang Liu, Rui Heng Yang, Vanessa Courville, Chao Xing, Vahid Partovi Nia

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

Is Integer Arithmetic Enough for Deep Learning Training?


Jul 18, 2022
Alireza Ghaffari, Marzieh S. Tahaei, Mohammadreza Tayaranian, Masoud Asgharian, Vahid Partovi Nia

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

Rethinking Pareto Frontier for Performance Evaluation of Deep Neural Networks


Feb 18, 2022
Vahid Partovi Nia, Alireza Ghaffari, Mahdi Zolnouri, Yvon Savaria

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
>>