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 Abhishek Gupta

Abhishek Gupta

Montreal AI Ethics Institute and Microsoft

Making Responsible AI the Norm rather than the Exception


Jan 31, 2021
Abhishek Gupta

* A report prepared by the Montreal AI Ethics Institute for the National Security Commission on Artificial Intelligence in response to their Key Considerations for Responsible Development and Fielding of Artificial Intelligence document; 26 pages 
  Access Paper or Ask Questions

Can Transfer Neuroevolution Tractably Solve Your Differential Equations?


Jan 06, 2021
Jian Cheng Wong, Abhishek Gupta, Yew-Soon Ong

Figure 1 for Can Transfer Neuroevolution Tractably Solve Your Differential Equations?
Figure 2 for Can Transfer Neuroevolution Tractably Solve Your Differential Equations?
Figure 3 for Can Transfer Neuroevolution Tractably Solve Your Differential Equations?
Figure 4 for Can Transfer Neuroevolution Tractably Solve Your Differential Equations?
* Currently under review at IEEE Computational Intelligence Magazine 
  Access Paper or Ask Questions

Scalable Transfer Evolutionary Optimization: Coping with Big Task Instances


Dec 03, 2020
Mojtaba Shakeri, Erfan Miahi, Abhishek Gupta, Yew-Soon Ong

Figure 1 for Scalable Transfer Evolutionary Optimization: Coping with Big Task Instances
Figure 2 for Scalable Transfer Evolutionary Optimization: Coping with Big Task Instances
Figure 3 for Scalable Transfer Evolutionary Optimization: Coping with Big Task Instances
Figure 4 for Scalable Transfer Evolutionary Optimization: Coping with Big Task Instances
* 12 pages, 5 figures, 2 tables, 2 algorithm pseudocodes 
  Access Paper or Ask Questions

The State of AI Ethics Report (October 2020)


Nov 05, 2020
Abhishek Gupta, Alexandrine Royer, Victoria Heath, Connor Wright, Camylle Lanteigne, Allison Cohen, Marianna Bergamaschi Ganapini, Muriam Fancy, Erick Galinkin, Ryan Khurana, Mo Akif, Renjie Butalid, Falaah Arif Khan, Masa Sweidan, Audrey Balogh

* 158 pages 
  Access Paper or Ask Questions

Providing Actionable Feedback in Hiring Marketplaces using Generative Adversarial Networks


Oct 06, 2020
Daniel Nemirovsky, Nicolas Thiebaut, Ye Xu, Abhishek Gupta

Figure 1 for Providing Actionable Feedback in Hiring Marketplaces using Generative Adversarial Networks
Figure 2 for Providing Actionable Feedback in Hiring Marketplaces using Generative Adversarial Networks
Figure 3 for Providing Actionable Feedback in Hiring Marketplaces using Generative Adversarial Networks
Figure 4 for Providing Actionable Feedback in Hiring Marketplaces using Generative Adversarial Networks
* 5 pages, 2 figures 
  Access Paper or Ask Questions

Report prepared by the Montreal AI Ethics Institute (MAIEI) on Publication Norms for Responsible AI


Oct 04, 2020
Abhishek Gupta, Camylle Lanteigne, Victoria Heath

* Report submitted to Partnership on AI for inclusion in their work on Publishing Norms for Responsible AI 
  Access Paper or Ask Questions

Report prepared by the Montreal AI Ethics Institute (MAIEI) for Publication Norms for Responsible AI by Partnership on AI


Sep 15, 2020
Abhishek Gupta, Camylle Lanteigne, Victoria Heath

* Report submitted to Partnership on AI for inclusion in their work on Publishing Norms for Responsible AI 
  Access Paper or Ask Questions

CounteRGAN: Generating Realistic Counterfactuals with Residual Generative Adversarial Nets


Sep 11, 2020
Daniel Nemirovsky, Nicolas Thiebaut, Ye Xu, Abhishek Gupta

Figure 1 for CounteRGAN: Generating Realistic Counterfactuals with Residual Generative Adversarial Nets
Figure 2 for CounteRGAN: Generating Realistic Counterfactuals with Residual Generative Adversarial Nets
Figure 3 for CounteRGAN: Generating Realistic Counterfactuals with Residual Generative Adversarial Nets
Figure 4 for CounteRGAN: Generating Realistic Counterfactuals with Residual Generative Adversarial Nets
* 12 pages 
  Access Paper or Ask Questions

Defending Adversarial Attacks without Adversarial Attacks in Deep Reinforcement Learning


Aug 14, 2020
Xinghua Qu, Yew-Soon Ong, Abhishek Gupta, Zhu Sun

Figure 1 for Defending Adversarial Attacks without Adversarial Attacks in Deep Reinforcement Learning
Figure 2 for Defending Adversarial Attacks without Adversarial Attacks in Deep Reinforcement Learning
Figure 3 for Defending Adversarial Attacks without Adversarial Attacks in Deep Reinforcement Learning
Figure 4 for Defending Adversarial Attacks without Adversarial Attacks in Deep Reinforcement Learning

  Access Paper or Ask Questions

Report prepared by the Montreal AI Ethics Institute In Response to Mila's Proposal for a Contact Tracing App


Aug 11, 2020
Allison Cohen, Abhishek Gupta

* 8 pages 
  Access Paper or Ask Questions

Green Lighting ML: Confidentiality, Integrity, and Availability of Machine Learning Systems in Deployment


Jul 09, 2020
Abhishek Gupta, Erick Galinkin

* 2 pages 
  Access Paper or Ask Questions

Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift


Jul 06, 2020
Marvin Zhang, Henrik Marklund, Abhishek Gupta, Sergey Levine, Chelsea Finn

Figure 1 for Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift
Figure 2 for Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift
Figure 3 for Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift
Figure 4 for Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift
* Project website: https://sites.google.com/view/adaptive-risk-minimization ; Code: https://github.com/henrikmarklund/arm 
  Access Paper or Ask Questions

The State of AI Ethics Report (June 2020)


Jun 25, 2020
Abhishek Gupta, Camylle Lanteigne, Victoria Heath, Marianna Bergamaschi Ganapini, Erick Galinkin, Allison Cohen, Tania De Gasperis, Mo Akif, Renjie Butalid

* 128 pages 
  Access Paper or Ask Questions

Befriending The Byzantines Through Reputation Scores


Jun 24, 2020
Jayanth Regatti, Abhishek Gupta

Figure 1 for Befriending The Byzantines Through Reputation Scores
Figure 2 for Befriending The Byzantines Through Reputation Scores
Figure 3 for Befriending The Byzantines Through Reputation Scores
Figure 4 for Befriending The Byzantines Through Reputation Scores

  Access Paper or Ask Questions

Ecological Reinforcement Learning


Jun 22, 2020
John D. Co-Reyes, Suvansh Sanjeev, Glen Berseth, Abhishek Gupta, Sergey Levine

Figure 1 for Ecological Reinforcement Learning
Figure 2 for Ecological Reinforcement Learning
Figure 3 for Ecological Reinforcement Learning
Figure 4 for Ecological Reinforcement Learning
* Preprint. Website at: https://sites.google.com/view/ecological-rl/home 
  Access Paper or Ask Questions

Response by the Montreal AI Ethics Institute to the European Commission's Whitepaper on AI


Jun 16, 2020
Abhishek Gupta, Camylle Lanteigne

* Submitted to the European Commission 
  Access Paper or Ask Questions

Accelerating Online Reinforcement Learning with Offline Datasets


Jun 16, 2020
Ashvin Nair, Murtaza Dalal, Abhishek Gupta, Sergey Levine

Figure 1 for Accelerating Online Reinforcement Learning with Offline Datasets
Figure 2 for Accelerating Online Reinforcement Learning with Offline Datasets
Figure 3 for Accelerating Online Reinforcement Learning with Offline Datasets
Figure 4 for Accelerating Online Reinforcement Learning with Offline Datasets
* 16 pages. Website: https://awacrl.github.io/ 
  Access Paper or Ask Questions

The Social Contract for AI


Jun 15, 2020
Mirka Snyder Caron, Abhishek Gupta

* Accepted paper for presentation at the IJCAI 2019 AI for Social Good workshop 
  Access Paper or Ask Questions

SECure: A Social and Environmental Certificate for AI Systems


Jun 11, 2020
Abhishek Gupta, Camylle Lanteigne, Sara Kingsley

* Accepted for presentation at the Canadian Society for Ecological Economics 2020 Research Symposium 
  Access Paper or Ask Questions

The Ingredients of Real-World Robotic Reinforcement Learning


Apr 27, 2020
Henry Zhu, Justin Yu, Abhishek Gupta, Dhruv Shah, Kristian Hartikainen, Avi Singh, Vikash Kumar, Sergey Levine

Figure 1 for The Ingredients of Real-World Robotic Reinforcement Learning
Figure 2 for The Ingredients of Real-World Robotic Reinforcement Learning
Figure 3 for The Ingredients of Real-World Robotic Reinforcement Learning
Figure 4 for The Ingredients of Real-World Robotic Reinforcement Learning
* First three authors contributed equally. Accepted as a spotlight presentation at ICLR 2020 
  Access Paper or Ask Questions

Convergence of Recursive Stochastic Algorithms using Wasserstein Divergence


Mar 25, 2020
Abhishek Gupta, William B. Haskell

* 32 pages, submitted to SIMODS 
  Access Paper or Ask Questions

DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction


Mar 16, 2020
Aviral Kumar, Abhishek Gupta, Sergey Levine

Figure 1 for DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction
Figure 2 for DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction
Figure 3 for DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction
Figure 4 for DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction
* Pre-print 
  Access Paper or Ask Questions

Learning in Markov Decision Processes under Constraints


Feb 27, 2020
Rahul Singh, Abhishek Gupta, Ness B. Shroff


  Access Paper or Ask Questions

Gradient Surgery for Multi-Task Learning


Jan 19, 2020
Tianhe Yu, Saurabh Kumar, Abhishek Gupta, Sergey Levine, Karol Hausman, Chelsea Finn

Figure 1 for Gradient Surgery for Multi-Task Learning
Figure 2 for Gradient Surgery for Multi-Task Learning
Figure 3 for Gradient Surgery for Multi-Task Learning
Figure 4 for Gradient Surgery for Multi-Task Learning

  Access Paper or Ask Questions

Learning To Reach Goals Without Reinforcement Learning


Dec 13, 2019
Dibya Ghosh, Abhishek Gupta, Justin Fu, Ashwin Reddy, Coline Devin, Benjamin Eysenbach, Sergey Levine

Figure 1 for Learning To Reach Goals Without Reinforcement Learning
Figure 2 for Learning To Reach Goals Without Reinforcement Learning
Figure 3 for Learning To Reach Goals Without Reinforcement Learning
Figure 4 for Learning To Reach Goals Without Reinforcement Learning
* First two authors contributed equally 
  Access Paper or Ask Questions

Unsupervised Curricula for Visual Meta-Reinforcement Learning


Dec 09, 2019
Allan Jabri, Kyle Hsu, Ben Eysenbach, Abhishek Gupta, Sergey Levine, Chelsea Finn

Figure 1 for Unsupervised Curricula for Visual Meta-Reinforcement Learning
Figure 2 for Unsupervised Curricula for Visual Meta-Reinforcement Learning
Figure 3 for Unsupervised Curricula for Visual Meta-Reinforcement Learning
Figure 4 for Unsupervised Curricula for Visual Meta-Reinforcement Learning
* NeurIPS 2019 
  Access Paper or Ask Questions

Minimalistic Attacks: How Little it Takes to Fool a Deep Reinforcement Learning Policy


Nov 22, 2019
Xinghua Qu, Zhu Sun, Yew-Soon Ong, Pengfei Wei, Abhishek Gupta

Figure 1 for Minimalistic Attacks: How Little it Takes to Fool a Deep Reinforcement Learning Policy
Figure 2 for Minimalistic Attacks: How Little it Takes to Fool a Deep Reinforcement Learning Policy
Figure 3 for Minimalistic Attacks: How Little it Takes to Fool a Deep Reinforcement Learning Policy
Figure 4 for Minimalistic Attacks: How Little it Takes to Fool a Deep Reinforcement Learning Policy

  Access Paper or Ask Questions

A Multi-Task Gradient Descent Method for Multi-Label Learning


Nov 19, 2019
Lu Bai, Yew-Soon Ong, Tiantian He, Abhishek Gupta

Figure 1 for A Multi-Task Gradient Descent Method for Multi-Label Learning
Figure 2 for A Multi-Task Gradient Descent Method for Multi-Label Learning
Figure 3 for A Multi-Task Gradient Descent Method for Multi-Label Learning
Figure 4 for A Multi-Task Gradient Descent Method for Multi-Label Learning

  Access Paper or Ask Questions