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 Hossein Mobahi

Hossein Mobahi
Alert button

Google Research

On student-teacher deviations in distillation: does it pay to disobey?


Jan 30, 2023
Vaishnavh Nagarajan, Aditya Krishna Menon, Srinadh Bhojanapalli, Hossein Mobahi, Sanjiv Kumar

Add code
Alert button

Figure 1 for On student-teacher deviations in distillation: does it pay to disobey?
Figure 2 for On student-teacher deviations in distillation: does it pay to disobey?
Figure 3 for On student-teacher deviations in distillation: does it pay to disobey?
Figure 4 for On student-teacher deviations in distillation: does it pay to disobey?

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

Sharpness-Aware Minimization Improves Language Model Generalization


Oct 16, 2021
Dara Bahri, Hossein Mobahi, Yi Tay

Add code
Alert button

Figure 1 for Sharpness-Aware Minimization Improves Language Model Generalization
Figure 2 for Sharpness-Aware Minimization Improves Language Model Generalization
Figure 3 for Sharpness-Aware Minimization Improves Language Model Generalization
Figure 4 for Sharpness-Aware Minimization Improves Language Model Generalization

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

The Low-Rank Simplicity Bias in Deep Networks


Mar 18, 2021
Minyoung Huh, Hossein Mobahi, Richard Zhang, Brian Cheung, Pulkit Agrawal, Phillip Isola

Add code
Alert button

Figure 1 for The Low-Rank Simplicity Bias in Deep Networks
Figure 2 for The Low-Rank Simplicity Bias in Deep Networks
Figure 3 for The Low-Rank Simplicity Bias in Deep Networks
Figure 4 for The Low-Rank Simplicity Bias in Deep Networks

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

NeurIPS 2020 Competition: Predicting Generalization in Deep Learning


Dec 14, 2020
Yiding Jiang, Pierre Foret, Scott Yak, Daniel M. Roy, Hossein Mobahi, Gintare Karolina Dziugaite, Samy Bengio, Suriya Gunasekar, Isabelle Guyon, Behnam Neyshabur

Add code
Alert button

Figure 1 for NeurIPS 2020 Competition: Predicting Generalization in Deep Learning
* 20 pages, 2 figures. Accepted for NeurIPS 2020 Competitions Track. Lead organizer: Yiding Jiang 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Data Augmentation via Structured Adversarial Perturbations


Nov 05, 2020
Calvin Luo, Hossein Mobahi, Samy Bengio

Add code
Alert button

Figure 1 for Data Augmentation via Structured Adversarial Perturbations
Figure 2 for Data Augmentation via Structured Adversarial Perturbations
Figure 3 for Data Augmentation via Structured Adversarial Perturbations
Figure 4 for Data Augmentation via Structured Adversarial Perturbations

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

A Unifying View on Implicit Bias in Training Linear Neural Networks


Oct 06, 2020
Chulhee Yun, Shankar Krishnan, Hossein Mobahi

Add code
Alert button

Figure 1 for A Unifying View on Implicit Bias in Training Linear Neural Networks
Figure 2 for A Unifying View on Implicit Bias in Training Linear Neural Networks
* 40 pages, 6 figures 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Sharpness-Aware Minimization for Efficiently Improving Generalization


Oct 03, 2020
Pierre Foret, Ariel Kleiner, Hossein Mobahi, Behnam Neyshabur

Add code
Alert button

Figure 1 for Sharpness-Aware Minimization for Efficiently Improving Generalization
Figure 2 for Sharpness-Aware Minimization for Efficiently Improving Generalization
Figure 3 for Sharpness-Aware Minimization for Efficiently Improving Generalization
Figure 4 for Sharpness-Aware Minimization for Efficiently Improving Generalization

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

Self-Distillation Amplifies Regularization in Hilbert Space


Feb 25, 2020
Hossein Mobahi, Mehrdad Farajtabar, Peter L. Bartlett

Add code
Alert button

Figure 1 for Self-Distillation Amplifies Regularization in Hilbert Space
Figure 2 for Self-Distillation Amplifies Regularization in Hilbert Space
Figure 3 for Self-Distillation Amplifies Regularization in Hilbert Space
Figure 4 for Self-Distillation Amplifies Regularization in Hilbert Space

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

Fantastic Generalization Measures and Where to Find Them


Dec 04, 2019
Yiding Jiang, Behnam Neyshabur, Hossein Mobahi, Dilip Krishnan, Samy Bengio

Add code
Alert button

Figure 1 for Fantastic Generalization Measures and Where to Find Them
Figure 2 for Fantastic Generalization Measures and Where to Find Them
Figure 3 for Fantastic Generalization Measures and Where to Find Them
Figure 4 for Fantastic Generalization Measures and Where to Find Them

   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
>>