Publications

Crowdsourcing

1. Adaptive Crowdsourcing Via Self-Supervised Learning
   A.K., Henrik Marklund, Benjamin Van Roy, Hong Jun Jeon, Richard Zeckhauser
   [Preprint]

Multi-Armed Bandits

1. Statistically Robust, Risk-Averse Best Arm Identification in Multi-Armed Bandits
   A.K., Jayakrishnan Nair, Krishna Jagannathan
   IEEE Transactions On Information Theory [Paper]

2. Constrained regret minimization for multi-criterion multi-armed bandits
   A.K., Jayakrishnan Nair, Krishna Jagannathan
   Springer Machine Learning
   [Paper]

3. Bandit algorithms: Letting go of logarithmic regret for statistical robustness
   Kumar Ashutosh, Jayakrishnan Nair, A.K., Krishna Jagannathan
   AISTATS 2021
   [Paper]

4. Distribution oblivious, risk-aware algorithms for multi-armed bandits with unbounded rewards
   A.K., Jayakrishnan Nair, Krishna Jagannathan
   NeurIPS 2019 [Paper]

Queueing Theory

1. “Please come back later”: Benefiting from deferrals in service systems
   A.K. and Jayakrishnan Nair
   COMSNETS 2020 [Paper]