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 Benjamin L. Edelman

Benjamin L. Edelman
Alert button

Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit


Jul 18, 2022
Boaz Barak, Benjamin L. Edelman, Surbhi Goel, Sham Kakade, Eran Malach, Cyril Zhang

Add code
Alert button

Figure 1 for Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit
Figure 2 for Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit
Figure 3 for Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit
Figure 4 for Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit

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

Inductive Biases and Variable Creation in Self-Attention Mechanisms


Oct 19, 2021
Benjamin L. Edelman, Surbhi Goel, Sham Kakade, Cyril Zhang

Add code
Alert button

Figure 1 for Inductive Biases and Variable Creation in Self-Attention Mechanisms
Figure 2 for Inductive Biases and Variable Creation in Self-Attention Mechanisms
Figure 3 for Inductive Biases and Variable Creation in Self-Attention Mechanisms
Figure 4 for Inductive Biases and Variable Creation in Self-Attention Mechanisms

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

SGD on Neural Networks Learns Functions of Increasing Complexity


May 28, 2019
Preetum Nakkiran, Gal Kaplun, Dimitris Kalimeris, Tristan Yang, Benjamin L. Edelman, Fred Zhang, Boaz Barak

Add code
Alert button

Figure 1 for SGD on Neural Networks Learns Functions of Increasing Complexity
Figure 2 for SGD on Neural Networks Learns Functions of Increasing Complexity
Figure 3 for SGD on Neural Networks Learns Functions of Increasing Complexity
Figure 4 for SGD on Neural Networks Learns Functions of Increasing Complexity
* Submitted to NeurIPS 2019 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email