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 Hrayr Harutyunyan

Hrayr Harutyunyan
Alert button

A Meta-Learning Approach to Predicting Performance and Data Requirements


Mar 02, 2023
Achin Jain, Gurumurthy Swaminathan, Paolo Favaro, Hao Yang, Avinash Ravichandran, Hrayr Harutyunyan, Alessandro Achille, Onkar Dabeer, Bernt Schiele, Ashwin Swaminathan, Stefano Soatto

Add code
Alert button

Figure 1 for A Meta-Learning Approach to Predicting Performance and Data Requirements
Figure 2 for A Meta-Learning Approach to Predicting Performance and Data Requirements
Figure 3 for A Meta-Learning Approach to Predicting Performance and Data Requirements
Figure 4 for A Meta-Learning Approach to Predicting Performance and Data Requirements
* CVPR 2023 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Supervision Complexity and its Role in Knowledge Distillation


Jan 28, 2023
Hrayr Harutyunyan, Ankit Singh Rawat, Aditya Krishna Menon, Seungyeon Kim, Sanjiv Kumar

Add code
Alert button

Figure 1 for Supervision Complexity and its Role in Knowledge Distillation
Figure 2 for Supervision Complexity and its Role in Knowledge Distillation
Figure 3 for Supervision Complexity and its Role in Knowledge Distillation
Figure 4 for Supervision Complexity and its Role in Knowledge Distillation
* Published at ICLR 2023 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Formal limitations of sample-wise information-theoretic generalization bounds


May 13, 2022
Hrayr Harutyunyan, Greg Ver Steeg, Aram Galstyan

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

Failure Modes of Domain Generalization Algorithms


Nov 26, 2021
Tigran Galstyan, Hrayr Harutyunyan, Hrant Khachatrian, Greg Ver Steeg, Aram Galstyan

Add code
Alert button

Figure 1 for Failure Modes of Domain Generalization Algorithms
Figure 2 for Failure Modes of Domain Generalization Algorithms
Figure 3 for Failure Modes of Domain Generalization Algorithms
Figure 4 for Failure Modes of Domain Generalization Algorithms

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

Information-theoretic generalization bounds for black-box learning algorithms


Oct 05, 2021
Hrayr Harutyunyan, Maxim Raginsky, Greg Ver Steeg, Aram Galstyan

Add code
Alert button

Figure 1 for Information-theoretic generalization bounds for black-box learning algorithms
Figure 2 for Information-theoretic generalization bounds for black-box learning algorithms
Figure 3 for Information-theoretic generalization bounds for black-box learning algorithms
Figure 4 for Information-theoretic generalization bounds for black-box learning algorithms
* NeurIPS 2021 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Estimating informativeness of samples with Smooth Unique Information


Jan 17, 2021
Hrayr Harutyunyan, Alessandro Achille, Giovanni Paolini, Orchid Majumder, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto

Add code
Alert button

Figure 1 for Estimating informativeness of samples with Smooth Unique Information
Figure 2 for Estimating informativeness of samples with Smooth Unique Information
Figure 3 for Estimating informativeness of samples with Smooth Unique Information
Figure 4 for Estimating informativeness of samples with Smooth Unique Information
* ICLR 2021, 22 pages 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Improving Generalization by Controlling Label-Noise Information in Neural Network Weights


Feb 19, 2020
Hrayr Harutyunyan, Kyle Reing, Greg Ver Steeg, Aram Galstyan

Add code
Alert button

Figure 1 for Improving Generalization by Controlling Label-Noise Information in Neural Network Weights
Figure 2 for Improving Generalization by Controlling Label-Noise Information in Neural Network Weights
Figure 3 for Improving Generalization by Controlling Label-Noise Information in Neural Network Weights
Figure 4 for Improving Generalization by Controlling Label-Noise Information in Neural Network Weights

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

Efficient Covariance Estimation from Temporal Data


May 30, 2019
Hrayr Harutyunyan, Daniel Moyer, Hrant Khachatrian, Greg Ver Steeg, Aram Galstyan

Add code
Alert button

Figure 1 for Efficient Covariance Estimation from Temporal Data
Figure 2 for Efficient Covariance Estimation from Temporal Data
Figure 3 for Efficient Covariance Estimation from Temporal Data
Figure 4 for Efficient Covariance Estimation from Temporal Data

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

MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing


May 28, 2019
Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor, Nazanin Alipourfard, Kristina Lerman, Hrayr Harutyunyan, Greg Ver Steeg, Aram Galstyan

Add code
Alert button

Figure 1 for MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing

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

MixHop: Higher-Order Graph Convolution Architectures via Sparsified Neighborhood Mixing


Apr 30, 2019
Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor, Hrayr Harutyunyan, Nazanin Alipourfard, Kristina Lerman, Greg Ver Steeg, Aram Galstyan

Add code
Alert button

Figure 1 for MixHop: Higher-Order Graph Convolution Architectures via Sparsified Neighborhood Mixing
* International Conference on Machine Learning, 2019 
   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
>>