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 Vimal Thilak

Vimal Thilak
Alert button

The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon


Jun 13, 2022
Vimal Thilak, Etai Littwin, Shuangfei Zhai, Omid Saremi, Roni Paiss, Joshua Susskind

Add code
Alert button

Figure 1 for The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon
Figure 2 for The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon
Figure 3 for The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon
Figure 4 for The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon
* Removed Tex formatting commands in title Title and Abstract 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Implicit Greedy Rank Learning in Autoencoders via Overparameterized Linear Networks


Jul 02, 2021
Shih-Yu Sun, Vimal Thilak, Etai Littwin, Omid Saremi, Joshua M. Susskind

Add code
Alert button

Figure 1 for Implicit Greedy Rank Learning in Autoencoders via Overparameterized Linear Networks
Figure 2 for Implicit Greedy Rank Learning in Autoencoders via Overparameterized Linear Networks
Figure 3 for Implicit Greedy Rank Learning in Autoencoders via Overparameterized Linear Networks
Figure 4 for Implicit Greedy Rank Learning in Autoencoders via Overparameterized Linear Networks

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

Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottlenecks


Jul 02, 2021
Etai Littwin, Omid Saremi, Shuangfei Zhai, Vimal Thilak, Hanlin Goh, Joshua M. Susskind, Greg Yang

Add code
Alert button

Figure 1 for Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottlenecks
Figure 2 for Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottlenecks
Figure 3 for Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottlenecks
Figure 4 for Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottlenecks

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