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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Maksim Velikanov

Maksim Velikanov
Alert button

A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta


Jun 22, 2022
Maksim Velikanov, Denis Kuznedelev, Dmitry Yarotsky

Add code
Alert button

Figure 1 for A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta
Figure 2 for A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta
Figure 3 for A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta
Figure 4 for A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Embedded Ensembles: Infinite Width Limit and Operating Regimes


Feb 24, 2022
Maksim Velikanov, Roman Kail, Ivan Anokhin, Roman Vashurin, Maxim Panov, Alexey Zaytsev, Dmitry Yarotsky

Add code
Alert button

Figure 1 for Embedded Ensembles: Infinite Width Limit and Operating Regimes
Figure 2 for Embedded Ensembles: Infinite Width Limit and Operating Regimes
Figure 3 for Embedded Ensembles: Infinite Width Limit and Operating Regimes
Figure 4 for Embedded Ensembles: Infinite Width Limit and Operating Regimes

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Tight Convergence Rate Bounds for Optimization Under Power Law Spectral Conditions


Feb 02, 2022
Maksim Velikanov, Dmitry Yarotsky

Add code
Alert button


   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Universal scaling laws in the gradient descent training of neural networks


May 02, 2021
Maksim Velikanov, Dmitry Yarotsky

Add code
Alert button

Figure 1 for Universal scaling laws in the gradient descent training of neural networks
Figure 2 for Universal scaling laws in the gradient descent training of neural networks
Figure 3 for Universal scaling laws in the gradient descent training of neural networks
Figure 4 for Universal scaling laws in the gradient descent training of neural networks

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email