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 Varun Kanade

Varun Kanade
Alert button

Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions


Nov 22, 2022
Satwik Bhattamishra, Arkil Patel, Varun Kanade, Phil Blunsom

Add code
Alert button

Figure 1 for Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions
Figure 2 for Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions
Figure 3 for Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions
Figure 4 for Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions
* Preprint 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

When are Local Queries Useful for Robust Learning?


Oct 12, 2022
Pascale Gourdeau, Varun Kanade, Marta Kwiatkowska, James Worrell

Add code
Alert button

* Accepted to NeurIPS 2022 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Partial Matrix Completion


Aug 25, 2022
Varun Kanade, Elad Hazan, Adam Tauman Kalai

Add code
Alert button

Figure 1 for Partial Matrix Completion

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

Beyond Impossibility: Balancing Sufficiency, Separation and Accuracy


May 24, 2022
Limor Gultchin, Vincent Cohen-Addad, Sophie Giffard-Roisin, Varun Kanade, Frederik Mallmann-Trenn

Add code
Alert button

Figure 1 for Beyond Impossibility: Balancing Sufficiency, Separation and Accuracy
Figure 2 for Beyond Impossibility: Balancing Sufficiency, Separation and Accuracy
Figure 3 for Beyond Impossibility: Balancing Sufficiency, Separation and Accuracy
Figure 4 for Beyond Impossibility: Balancing Sufficiency, Separation and Accuracy

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

Sample Complexity Bounds for Robustly Learning Decision Lists against Evasion Attacks


May 12, 2022
Pascale Gourdeau, Varun Kanade, Marta Kwiatkowska, James Worrell

Add code
Alert button

* To appear in the proceedings of International Joint Conference on Artificial Intelligence (2022) 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Exponential Tail Local Rademacher Complexity Risk Bounds Without the Bernstein Condition


Feb 23, 2022
Varun Kanade, Patrick Rebeschini, Tomas Vaskevicius

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

Towards optimally abstaining from prediction


May 28, 2021
Adam Tauman Kalai, Varun Kanade

Add code
Alert button

Figure 1 for Towards optimally abstaining from prediction
* 23 pages 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Efficient Learning with Arbitrary Covariate Shift


Feb 15, 2021
Adam Kalai, Varun Kanade

Add code
Alert button

Figure 1 for Efficient Learning with Arbitrary Covariate Shift

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

Lottery Tickets in Linear Models: An Analysis of Iterative Magnitude Pruning


Aug 06, 2020
Bryn Elesedy, Varun Kanade, Yee Whye Teh

Add code
Alert button

Figure 1 for Lottery Tickets in Linear Models: An Analysis of Iterative Magnitude Pruning
* 16 pages, 1 figure. Corrections to previous version 
   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
>>