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 Soheil Feizi

Soheil Feizi
Alert button

Robustness Certificates Against Adversarial Examples for ReLU Networks


Feb 05, 2019
Sahil Singla, Soheil Feizi

Add code
Alert button

Figure 1 for Robustness Certificates Against Adversarial Examples for ReLU Networks
Figure 2 for Robustness Certificates Against Adversarial Examples for ReLU Networks
Figure 3 for Robustness Certificates Against Adversarial Examples for ReLU Networks
Figure 4 for Robustness Certificates Against Adversarial Examples for ReLU Networks

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

Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation


Feb 01, 2019
Yogesh Balaji, Rama Chellappa, Soheil Feizi

Add code
Alert button

Figure 1 for Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation
Figure 2 for Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation
Figure 3 for Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation
Figure 4 for Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation

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

Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation


Feb 01, 2019
Sahil Singla, Eric Wallace, Shi Feng, Soheil Feizi

Add code
Alert button

Figure 1 for Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation
Figure 2 for Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation
Figure 3 for Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation
Figure 4 for Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation

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

Compressing GANs using Knowledge Distillation


Feb 01, 2019
Angeline Aguinaldo, Ping-Yeh Chiang, Alex Gain, Ameya Patil, Kolten Pearson, Soheil Feizi

Add code
Alert button

Figure 1 for Compressing GANs using Knowledge Distillation
Figure 2 for Compressing GANs using Knowledge Distillation
Figure 3 for Compressing GANs using Knowledge Distillation
Figure 4 for Compressing GANs using Knowledge Distillation

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

Understanding GANs: the LQG Setting


Oct 22, 2018
Soheil Feizi, Farzan Farnia, Tony Ginart, David Tse

Add code
Alert button

Figure 1 for Understanding GANs: the LQG Setting
Figure 2 for Understanding GANs: the LQG Setting
Figure 3 for Understanding GANs: the LQG Setting
Figure 4 for Understanding GANs: the LQG Setting

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

Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs


Oct 09, 2018
Yogesh Balaji, Hamed Hassani, Rama Chellappa, Soheil Feizi

Add code
Alert button

Figure 1 for Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs
Figure 2 for Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs
Figure 3 for Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs
Figure 4 for Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs

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

Are adversarial examples inevitable?


Sep 06, 2018
Ali Shafahi, W. Ronny Huang, Christoph Studer, Soheil Feizi, Tom Goldstein

Add code
Alert button

Figure 1 for Are adversarial examples inevitable?
Figure 2 for Are adversarial examples inevitable?
Figure 3 for Are adversarial examples inevitable?
Figure 4 for Are adversarial examples inevitable?

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

Porcupine Neural Networks: (Almost) All Local Optima are Global


Oct 05, 2017
Soheil Feizi, Hamid Javadi, Jesse Zhang, David Tse

Add code
Alert button

Figure 1 for Porcupine Neural Networks: (Almost) All Local Optima are Global
Figure 2 for Porcupine Neural Networks: (Almost) All Local Optima are Global
Figure 3 for Porcupine Neural Networks: (Almost) All Local Optima are Global
Figure 4 for Porcupine Neural Networks: (Almost) All Local Optima are Global

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

Maximum Likelihood Latent Space Embedding of Logistic Random Dot Product Graphs


Aug 30, 2017
Luke O'Connor, Muriel Médard, Soheil Feizi

Add code
Alert button

Figure 1 for Maximum Likelihood Latent Space Embedding of Logistic Random Dot Product Graphs
Figure 2 for Maximum Likelihood Latent Space Embedding of Logistic Random Dot Product Graphs
Figure 3 for Maximum Likelihood Latent Space Embedding of Logistic Random Dot Product Graphs
Figure 4 for Maximum Likelihood Latent Space Embedding of Logistic Random Dot Product Graphs

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

Maximally Correlated Principal Component Analysis


Feb 21, 2017
Soheil Feizi, David Tse

Add code
Alert button

Figure 1 for Maximally Correlated Principal Component Analysis
Figure 2 for Maximally Correlated Principal Component Analysis
Figure 3 for Maximally Correlated Principal Component Analysis
Figure 4 for Maximally Correlated Principal Component Analysis
* 35 pages, 5 figures 
   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
5
6
7
8
>>