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 Saurabh Garg

Saurabh Garg

Deconstructing Distributions: A Pointwise Framework of Learning


Feb 20, 2022
Gal Kaplun, Nikhil Ghosh, Saurabh Garg, Boaz Barak, Preetum Nakkiran

Figure 1 for Deconstructing Distributions: A Pointwise Framework of Learning
Figure 2 for Deconstructing Distributions: A Pointwise Framework of Learning
Figure 3 for Deconstructing Distributions: A Pointwise Framework of Learning
Figure 4 for Deconstructing Distributions: A Pointwise Framework of Learning
* GK and NG contributed equally 
  Access Paper or Ask Questions

Leveraging Unlabeled Data to Predict Out-of-Distribution Performance


Feb 09, 2022
Saurabh Garg, Sivaraman Balakrishnan, Zachary C. Lipton, Behnam Neyshabur, Hanie Sedghi

Figure 1 for Leveraging Unlabeled Data to Predict Out-of-Distribution Performance
Figure 2 for Leveraging Unlabeled Data to Predict Out-of-Distribution Performance
Figure 3 for Leveraging Unlabeled Data to Predict Out-of-Distribution Performance
Figure 4 for Leveraging Unlabeled Data to Predict Out-of-Distribution Performance
* Accepted at ICLR 2022 
  Access Paper or Ask Questions

Parallel Multi-Scale Networks with Deep Supervision for Hand Keypoint Detection


Dec 19, 2021
Renjie Li, Son Tran, Saurabh Garg, Katherine Lawler, Jane Alty, Quan Bai

Figure 1 for Parallel Multi-Scale Networks with Deep Supervision for Hand Keypoint Detection
Figure 2 for Parallel Multi-Scale Networks with Deep Supervision for Hand Keypoint Detection
Figure 3 for Parallel Multi-Scale Networks with Deep Supervision for Hand Keypoint Detection
Figure 4 for Parallel Multi-Scale Networks with Deep Supervision for Hand Keypoint Detection

  Access Paper or Ask Questions

Mixture Proportion Estimation and PU Learning: A Modern Approach


Nov 01, 2021
Saurabh Garg, Yifan Wu, Alex Smola, Sivaraman Balakrishnan, Zachary C. Lipton

Figure 1 for Mixture Proportion Estimation and PU Learning: A Modern Approach
Figure 2 for Mixture Proportion Estimation and PU Learning: A Modern Approach
Figure 3 for Mixture Proportion Estimation and PU Learning: A Modern Approach
Figure 4 for Mixture Proportion Estimation and PU Learning: A Modern Approach
* Spotlight at NeurIPS 2021 
  Access Paper or Ask Questions

RATT: Leveraging Unlabeled Data to Guarantee Generalization


May 01, 2021
Saurabh Garg, Sivaraman Balakrishnan, J. Zico Kolter, Zachary C. Lipton

Figure 1 for RATT: Leveraging Unlabeled Data to Guarantee Generalization
Figure 2 for RATT: Leveraging Unlabeled Data to Guarantee Generalization
Figure 3 for RATT: Leveraging Unlabeled Data to Guarantee Generalization
Figure 4 for RATT: Leveraging Unlabeled Data to Guarantee Generalization
* Pre-print 
  Access Paper or Ask Questions

Applications of Artificial Intelligence to aid detection of dementia: a narrative review on current capabilities and future directions


Apr 29, 2021
Renjie Li, Xinyi Wang, Katherine Lawler, Saurabh Garg, Quan Bai, Jane Alty

Figure 1 for Applications of Artificial Intelligence to aid detection of dementia: a narrative review on current capabilities and future directions
Figure 2 for Applications of Artificial Intelligence to aid detection of dementia: a narrative review on current capabilities and future directions
Figure 3 for Applications of Artificial Intelligence to aid detection of dementia: a narrative review on current capabilities and future directions
Figure 4 for Applications of Artificial Intelligence to aid detection of dementia: a narrative review on current capabilities and future directions
* 11 pages 
  Access Paper or Ask Questions

On Proximal Policy Optimization's Heavy-tailed Gradients


Feb 20, 2021
Saurabh Garg, Joshua Zhanson, Emilio Parisotto, Adarsh Prasad, J. Zico Kolter, Sivaraman Balakrishnan, Zachary C. Lipton, Ruslan Salakhutdinov, Pradeep Ravikumar

Figure 1 for On Proximal Policy Optimization's Heavy-tailed Gradients
Figure 2 for On Proximal Policy Optimization's Heavy-tailed Gradients
Figure 3 for On Proximal Policy Optimization's Heavy-tailed Gradients
Figure 4 for On Proximal Policy Optimization's Heavy-tailed Gradients
* Pre-print 
  Access Paper or Ask Questions

A Unified View of Label Shift Estimation


Mar 17, 2020
Saurabh Garg, Yifan Wu, Sivaraman Balakrishnan, Zachary C. Lipton

Figure 1 for A Unified View of Label Shift Estimation
Figure 2 for A Unified View of Label Shift Estimation
* Pre-print 
  Access Paper or Ask Questions

Code-switched Language Models Using Dual RNNs and Same-Source Pretraining


Sep 06, 2018
Saurabh Garg, Tanmay Parekh, Preethi Jyothi

Figure 1 for Code-switched Language Models Using Dual RNNs and Same-Source Pretraining
Figure 2 for Code-switched Language Models Using Dual RNNs and Same-Source Pretraining
Figure 3 for Code-switched Language Models Using Dual RNNs and Same-Source Pretraining
Figure 4 for Code-switched Language Models Using Dual RNNs and Same-Source Pretraining
* Accepted at EMNLP 2018 
  Access Paper or Ask Questions

Dual Language Models for Code Switched Speech Recognition


Aug 03, 2018
Saurabh Garg, Tanmay Parekh, Preethi Jyothi

Figure 1 for Dual Language Models for Code Switched Speech Recognition
Figure 2 for Dual Language Models for Code Switched Speech Recognition
Figure 3 for Dual Language Models for Code Switched Speech Recognition
Figure 4 for Dual Language Models for Code Switched Speech Recognition
* Accepted at Interspeech 2018 
  Access Paper or Ask Questions

A Linear Programming Driven Genetic Algorithm for Meta-Scheduling on Utility Grids


Mar 08, 2009
Saurabh Garg, Pramod Konugurthi, Rajkumar Buyya

Figure 1 for A Linear Programming Driven Genetic Algorithm for Meta-Scheduling on Utility Grids
Figure 2 for A Linear Programming Driven Genetic Algorithm for Meta-Scheduling on Utility Grids
Figure 3 for A Linear Programming Driven Genetic Algorithm for Meta-Scheduling on Utility Grids
Figure 4 for A Linear Programming Driven Genetic Algorithm for Meta-Scheduling on Utility Grids
* Proceedings of the 16th International Conference on Advanced Computing and Communication (ADCOM 2008, IEEE Press, New York, USA), Dec. 14-17, 2008, Chennai, India 
 * 9 pages 
  Access Paper or Ask Questions