Arun Rajkumar

Research Scientist


Arun Rajkumar received his bachelors in computer science from PSG College of technology in 2006 and his masters in computer science from the Indian institute of Science (IISc) in 2010. He continued for his Ph.D in computer science at IIsc where he was a Microsoft Research Ph.D fellow. Previously, he was a research scientist at Xerox research center, India where he worked on transportation related problems in online learning. He is currently a research scientist at the machine learning and analytics lab at Conduent labs, India. His research interests include statistical machine learning in general with a focus on ranking and online learning problems and their applications to business problems.


  • U. N. Niranjan, Arun Rajkumar: Inductive Pairwise Ranking: Going Beyond the n log(n) Barrier. AAAI 2017: 2436-2442

  • Arun Rajkumar, Shivani Agarwal: When can we rank well from comparisons of \(O(n\log(n))\) non-actively chosen pairs? COLT2016: 1376-1401

  • Himanshu S. Bhatt, Arun Rajkumar, Shourya Roy: Multi-Source Iterative Adaptation for Cross-Domain Classification. IJCAI 2016: 3691-3697

  • Siddartha Y. Ramamohan, Arun Rajkumar, Shivani Agarwal: Dueling Bandits: Beyond Condorcet Winners to General Tournament Solutions. NIPS 2016: 1253-1261

  • Arun Rajkumar, Suprovat Ghoshal, Lek-Heng Lim, Shivani Agarwal: Ranking from Stochastic Pairwise Preferences: Recovering Condorcet Winners and Tournament Solution Sets at the Top. ICML 2015: 665-673

  • Arun Rajkumar, Shivani Agarwal: A Statistical Convergence Perspective of Algorithms for Rank Aggregation from Pairwise Data. ICML 2014: 118-126