A
Arun Rajkumar
Researcher at Indian Institute of Technology Madras
Publications - 29
Citations - 425
Arun Rajkumar is an academic researcher from Indian Institute of Technology Madras. The author has contributed to research in topics: Pairwise comparison & Ranking. The author has an hindex of 7, co-authored 29 publications receiving 374 citations. Previous affiliations of Arun Rajkumar include Xerox & Indian Institute of Science.
Papers
More filters
Proceedings Article
A Statistical Convergence Perspective of Algorithms for Rank Aggregation from Pairwise Data
Arun Rajkumar,Shivani Agarwal +1 more
TL;DR: This paper shows that, under a 'time-reversibility' or Bradley-Terry-Luce (BTL) condition on the distribution, the rank centrality (PageRank) and least squares (HodgeRank) algorithms both converge to an optimal ranking.
Proceedings Article
A Differentially Private Stochastic Gradient Descent Algorithm for Multiparty Classification
Arun Rajkumar,Shivani Agarwal +1 more
TL;DR: A new differentially private algorithm for the multiparty setting that uses a stochastic gradient descent based procedure to directly optimize the overall multiparty objective rather than combining classifiers learned from optimizing local objectives.
Proceedings Article
Multi-source iterative adaptation for cross-domain classification
TL;DR: A novel multi-source iterative domain adaptation algorithm that leverages knowledge from selective sources to improve the performance in a target domain and significantly outperforms existing cross-domain classification approaches on the real world and benchmark datasets.
Proceedings Article
Dueling Bandits: Beyond Condorcet Winners to General Tournament Solutions
TL;DR: A family of UCB-style dueling bandit algorithms for general tournament solutions in social choice theory, which show anytime regret bounds for them and can achieve low regret relative to the target winning set of interest.
Proceedings Article
Ranking from Stochastic Pairwise Preferences: Recovering Condorcet Winners and Tournament Solution Sets at the Top
TL;DR: An improved sample complexity bound is obtained for the Rank Centrality algorithm to recover an optimal ranking under a Bradley-Terry-Luce (BTL) condition, which answers an open question of Rajkumar and Agarwal (2014).