1 code implementation • 9 Feb 2024 • Archit Sood, Shweta Jain, Sujit Gujar
However, they do not consider the distribution of pulls among the arms.
no code implementations • 8 Feb 2024 • Subham Pokhriyal, Shweta Jain, Ganesh Ghalme, Swapnil Dhamal, Sujit Gujar
At the first level, Bi-Level Fairness guarantees a certain minimum exposure to each group.
no code implementations • 5 Feb 2024 • Sambhav Solanki, Shweta Jain, Sujit Gujar
We design a novel communication protocol that allows for (i) Sub-linear theoretical bounds on fairness regret for Fed-FairX-LinUCB and comparable bounds for the private counterpart, Priv-FairX-LinUCB (relative to single-agent learning), (ii) Effective use of privacy budget in Priv-FairX-LinUCB.
no code implementations • 24 Jan 2024 • Sankarshan Damle, Manisha Padala, Sujit Gujar
As these blockchains are a public resource, it may be preferable to reduce these transaction fees.
no code implementations • 24 Feb 2023 • Sanjay Chandlekar, Arthik Boroju, Shweta Jain, Sujit Gujar
Finally, we showcase the efficacy of the proposed algorithm in mitigating demand peaks in a real-world smart grid system using the PowerTAC simulator as a test bed.
no code implementations • 25 Nov 2022 • Sankarshan Damle, Manisha Padala, Sujit Gujar
Further, funding the optimal social welfare subset of projects is desirable when every available project cannot be funded due to budget restrictions.
no code implementations • 27 Jun 2022 • Sambhav Solanki, Samhita Kanaparthy, Sankarshan Damle, Sujit Gujar
There is a rapid increase in the cooperative learning paradigm in online learning settings, i. e., federated learning (FL).
no code implementations • 8 Feb 2022 • Debojit Das, Shweta Jain, Sujit Gujar
With this reduction, we propose CBwK-LPUCB that uses PrimalDualBwK ingeniously.
1 code implementation • 6 Sep 2021 • Samhita Kanaparthy, Manisha Padala, Sankarshan Damle, Ravi Kiran Sarvadevabhatla, Sujit Gujar
F3 adopts multiple heuristics to improve fairness across different demographic groups without requiring data homogeneity assumption.
1 code implementation • 23 Aug 2021 • Manisha Padala, Sankarshan Damle, Sujit Gujar
Deep learning's unprecedented success raises several ethical concerns ranging from biased predictions to data privacy.
no code implementations • 3 Jun 2021 • Kumar Abhishek, Ganesh Ghalme, Sujit Gujar, Yadati Narahari
An algorithm can select a subset of arms from the \emph{availability set} (sleeping bandits) and receive the corresponding reward along with semi-bandit feedback (combinatorial bandits).
no code implementations • 9 Feb 2021 • Ayush Deva, Kumar Abhishek, Sujit Gujar
We show that after a certain number of rounds, $\tau$, \newalgo\ outputs a subset of agents that satisfy the average quality constraint with a high probability.
no code implementations • 8 Feb 2021 • Anurag Jain, Shoeb Siddiqui, Sujit Gujar
Due to varying network capacities, the slower nodes would be at a relative disadvantage compared to the faster ones, which could negatively impact their revenue.
Fairness Distributed, Parallel, and Cluster Computing Networking and Internet Architecture
no code implementations • 15 Apr 2020 • Manisha Padala, Debojit Das, Sujit Gujar
We aim to quantitatively and qualitatively study the effect of the dimension of the input noise on the performance of GANs.
no code implementations • 26 Feb 2020 • Kumar Abhishek, Shweta Jain, Sujit Gujar
It is in the best interest of the center to select an ad that has a high expected value (i. e., probability of getting a click $\times$ value it derives from a click of the ad).
no code implementations • 24 Jan 2020 • Ganesh Ghalme, Swapnil Dhamal, Shweta Jain, Sujit Gujar, Y. Narahari
In this paper, we introduce Ballooning Multi-Armed Bandits (BL-MAB), a novel extension of the classical stochastic MAB model.
no code implementations • 4 Oct 2019 • Kumar Abhishek, Sneha Maheshwari, Sujit Gujar
In this report, we aim to exemplify concentration inequalities and provide easy to understand proofs for it.
no code implementations • 10 Jun 2019 • Moin Hussain Moti, Dimitris Chatzopoulos, Pan Hui, Sujit Gujar
FaRM uses \textit{(i)} a \emph{report strength score} to remove the risk of random pairing with dishonest reporters, \textit{(ii)} a \emph{consistency score} to measure an agent's history of accurate reports and distinguish valuable reports, \textit{(iii)} a \emph{reliability score} to estimate the probability of an agent to collude with nearby agents and prevents agents from getting swayed, and \textit{(iv)} a \emph{location robustness score} to filter agents who try to participate without being present in the considered setting.
no code implementations • 1 Nov 2018 • Padala Manisha, Sujit Gujar
Surrogates serve only as an upper bound to the actual constraints, and convexifying fairness constraints might be challenging.
no code implementations • 31 Mar 2018 • P Manisha, Sujit Gujar
We compare and contrast different results and put forth a summary of theoretical contributions about GANs with focus on image/visual applications.
no code implementations • 27 Jun 2014 • Shweta Jain, Sujit Gujar, Satyanath Bhat, Onno Zoeter, Y. Narahari
First, we propose a framework, Assured Accuracy Bandit (AAB), which leads to an MAB algorithm, Constrained Confidence Bound for a Non Strategic setting (CCB-NS).