no code implementations • 11 Dec 2023 • Zeyu Shen, Anilesh Krishnaswamy, Janardhan Kulkarni, Kamesh Munagala
In this paper, we consider differentially private classification when some features are sensitive, while the rest of the features and the label are not.
no code implementations • 4 Nov 2022 • Aditya Bhaskara, Sreenivas Gollapudi, Sungjin Im, Kostas Kollias, Kamesh Munagala
For stochastic MAB, we also consider a stronger model where a probe reveals the reward values of the probed arms, and show that in this case, $k=3$ probes suffice to achieve parameter-independent constant regret, $O(n^2)$.
no code implementations • NeurIPS 2021 • Zeyu Shen, Lodewijk Gelauff, Ashish Goel, Aleksandra Korolova, Kamesh Munagala
We show in a formal sense that the Nash Welfare rule that maximizes product of agent values is uniquely positioned to be robust when diversity constraints are introduced, while almost all other natural allocation rules fail this criterion.
no code implementations • 18 Dec 2020 • Anilesh K. Krishnaswamy, Zhihao Jiang, Kangning Wang, Yu Cheng, Kamesh Munagala
Instead, we propose a fairness notion whose guarantee, on each group $g$ in a class $\mathcal{G}$, is relative to the performance of the best classifier on $g$.
no code implementations • NeurIPS 2020 • Aditya Bhaskara, Sreenivas Gollapudi, Kostas Kollias, Kamesh Munagala
Inspired by traffic routing applications, we consider the problem of finding the shortest path from a source $s$ to a destination $t$ in a graph, when the lengths of the edges are unknown.
no code implementations • 9 May 2019 • Xingyu Chen, Brandon Fain, Liang Lyu, Kamesh Munagala
We extend the fair machine learning literature by considering the problem of proportional centroid clustering in a metric context.
no code implementations • 12 Nov 2018 • Brandon Fain, Ashish Goel, Kamesh Munagala, Nina Prabhu
Constant sample complexity means that the mechanism (potentially randomized) only uses a constant number of ordinal queries regardless of the number of voters and alternatives.
1 code implementation • 2 Oct 2017 • Brandon Fain, Ashish Goel, Kamesh Munagala, Sukolsak Sakshuwong
In large scale collective decision making, social choice is a normative study of how one ought to design a protocol for reaching consensus.
Computer Science and Game Theory Multiagent Systems
no code implementations • 14 Jun 2013 • Sudipto Guha, Kamesh Munagala
We show that by restricting the state spaces of arms we can find single arm policies and that these single arm policies can be combined into global (near) index policies where the approximate version of the exchange property is true in expectation.
no code implementations • 4 Nov 2010 • Sudipto Guha, Kamesh Munagala, Martin Pal
We study this problem in the Bayesian setting.