1. | Sankarshan Damle; Padala Manisha; Sujit Gujar: Welfare Optimal Combinatorial Civic Crowdfunding with Budgeted Agents. Games, Agents and Incentives Workshop (GAIW'22)@AAMAS'22, 2022. (Type: Workshop | BibTeX | Tags: Civic Crowdfunding, Game Theory)@workshop{sankarshan2022a,
title = {Welfare Optimal Combinatorial Civic Crowdfunding with Budgeted Agents},
author = {Sankarshan Damle and Padala Manisha and Sujit Gujar},
year = {2022},
date = {2022-05-09},
booktitle = {Games, Agents and Incentives Workshop (GAIW'22)@AAMAS'22},
keywords = {Civic Crowdfunding, Game Theory},
pubstate = {published},
tppubtype = {workshop}
}
|
2. | Padala Manisha; Sankarshan Damle; Sujit Gujar: Building Ethical AI: Federated Learning meets Fairness and Privacy. First Indian Conference on Deployable AI, 2021. (Type: Conference | BibTeX | Tags: differential privacy, fairness, federated learning)@conference{manisha2021a,
title = {Building Ethical AI: Federated Learning meets Fairness and Privacy},
author = {Padala Manisha and Sankarshan Damle and Sujit Gujar },
year = {2021},
date = {2021-06-17},
booktitle = {First Indian Conference on Deployable AI},
keywords = {differential privacy, fairness, federated learning},
pubstate = {published},
tppubtype = {conference}
}
|
3. | Padala Manisha; Sujit Gujar: FNNC: Achieving Fairness through Neural Networks. The 29th International Joint Conference on Artificial Intelligence, IJCAI 2020, 2020. (Type: Conference | Abstract | BibTeX | Tags: fairness, Neural Networks)@conference{manisha2020a,
title = {FNNC: Achieving Fairness through Neural Networks},
author = {Padala Manisha and Sujit Gujar},
year = {2020},
date = {2020-07-11},
booktitle = {The 29th International Joint Conference on Artificial Intelligence, IJCAI 2020},
abstract = {The classification models ensure fairness by solving a constrained optimization problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and Equalized Odds, which are non-decomposable and non-convex. Researchers define convex surrogates of the constraints and then apply convex optimization frameworks to obtain fair classifiers. Surrogates serve only as an upper bound to the actual constraints, and convexifying fairness constraints might be challenging. We propose a neural network-based framework, emph{FNNC}, to achieve fairness while maintaining high accuracy in classification. The above fairness constraints are included in the loss using Lagrangian multipliers. We prove bounds on generalization errors for the constrained losses which asymptotically go to zero. The network is optimized using two-step mini-batch stochastic gradient descent. Our experiments show that FNNC performs as good as the state of the art, if not better. The experimental evidence supplements our theoretical guarantees. In summary, we have an automated solution to achieve fairness in classification, which is easily extendable to many fairness constraints.},
keywords = {fairness, Neural Networks},
pubstate = {published},
tppubtype = {conference}
}
The classification models ensure fairness by solving a constrained optimization problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and Equalized Odds, which are non-decomposable and non-convex. Researchers define convex surrogates of the constraints and then apply convex optimization frameworks to obtain fair classifiers. Surrogates serve only as an upper bound to the actual constraints, and convexifying fairness constraints might be challenging. We propose a neural network-based framework, emph{FNNC}, to achieve fairness while maintaining high accuracy in classification. The above fairness constraints are included in the loss using Lagrangian multipliers. We prove bounds on generalization errors for the constrained losses which asymptotically go to zero. The network is optimized using two-step mini-batch stochastic gradient descent. Our experiments show that FNNC performs as good as the state of the art, if not better. The experimental evidence supplements our theoretical guarantees. In summary, we have an automated solution to achieve fairness in classification, which is easily extendable to many fairness constraints. |
4. | Padala Manisha; Sujit Gujar: Thompson Sampling Based Multi-Armed-Bandit Mechanism Using Neural Networks. In: AAMAS, pp. 2111–2113, International Foundation for Autonomous Agents and Multiagent Systems, 2019. (Type: Conference | BibTeX | Tags: Multi-arm Bandits, Neural Networks)@inproceedings{DBLP:conf/atal/ManishaG19,
title = {Thompson Sampling Based Multi-Armed-Bandit Mechanism Using Neural Networks},
author = {Padala Manisha and Sujit Gujar},
year = {2019},
date = {2019-01-01},
booktitle = {AAMAS},
pages = {2111--2113},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems},
keywords = {Multi-arm Bandits, Neural Networks},
pubstate = {published},
tppubtype = {inproceedings}
}
|
5. | Padala Manisha; Jawahar C V; Sujit Gujar: Learning Optimal Redistribution Mechanisms Through Neural Networks. In: AAMAS, pp. 345–353, International Foundation for Autonomous Agents and Multiagent Systems Richland, SC, USA / ACM, 2018. (Type: Conference | BibTeX | Tags: Mechanism Design, Neural Networks)@inproceedings{DBLP:conf/atal/ManishaJG18,
title = {Learning Optimal Redistribution Mechanisms Through Neural Networks},
author = {Padala Manisha and C V Jawahar and Sujit Gujar},
year = {2018},
date = {2018-01-01},
booktitle = {AAMAS},
pages = {345--353},
publisher = {International Foundation for Autonomous Agents and Multiagent Systems Richland, SC, USA / ACM},
keywords = {Mechanism Design, Neural Networks},
pubstate = {published},
tppubtype = {inproceedings}
}
|
6. | Sankarshan Damle; Padala Manisha; Sujit Gujar: Welfare Optimal Combinatorial Civic Crowdfunding with Budgeted Agents. Games, Agents and Incentives Workshop, 0000. (Type: Workshop | BibTeX | Tags: Civic Crowdfunding)@workshop{damle22aoptMCC,
title = {Welfare Optimal Combinatorial Civic Crowdfunding with Budgeted Agents},
author = {Sankarshan Damle and Padala Manisha and Sujit Gujar},
booktitle = {Games, Agents and Incentives Workshop},
keywords = {Civic Crowdfunding},
pubstate = {published},
tppubtype = {workshop}
}
|