Sotabase

Career

· Visiting Faculty Researcher, Google2022–2023
· Amazon Scholar, Amazon2019–2021
· Associate Professor, Columbia University2015–
· Postdoctoral Researcher, Microsoft Research (MSR)2011–2013
· Research Intern, IBM Almaden Research Center2008–2008
· PhD in Computer Science, Stanford University2006–2011
· Member of Research Staff, Bell Labs Alcatel-Lucent2004–2006
· Software Engineer, Yahoo! Software India Pvt. Ltd.2004–2004
· M.E., Computer Science and Automation, Indian Institute of Science2002–2004
· B.E., Computer Science and Engineering, M.B.M. Engineering College1998–2002

Publications (61)

Thompson Sampling for Contextual Bandits with Linear Payoffs
International Conference on Machine Learning · 2012
1,090
cited
Further Optimal Regret Bounds for Thompson Sampling
International Conference on Artificial Intelligence and Statistics · 2012
454
cited
A Dynamic Near-Optimal Algorithm for Online Linear Programming
Operational Research · 2009
321
cited
A framework for high-accuracy privacy-preserving mining
IEEE International Conference on Data Engineering · 2004
234
cited
Optimistic posterior sampling for reinforcement learning: worst-case regret bounds
Neural Information Processing Systems · 2022
229
cited
Bandits with concave rewards and convex knapsacks
ACM Conference on Economics and Computation · 2014
214
cited
Reinforcement Learning for Integer Programming: Learning to Cut
International Conference on Machine Learning · 2019
209
cited
Fast Algorithms for Online Stochastic Convex Programming
ACM-SIAM Symposium on Discrete Algorithms · 2014
184
cited
Near-Optimal Regret Bounds for Thompson Sampling
Journal of the ACM · 2017
180
cited
A unified framework for dynamic pari-mutuel information market design
ACM Conference on Economics and Computation · 2009
177
cited
MNL-Bandit: A Dynamic Learning Approach to Assortment Selection
Operational Research · 2017
169
cited
Linear Contextual Bandits with Knapsacks
Neural Information Processing Systems · 2015
160
cited
Discretizing Continuous Action Space for On-Policy Optimization
AAAI Conference on Artificial Intelligence · 2019
143
cited
Bandits with Delayed, Aggregated Anonymous Feedback
International Conference on Machine Learning · 2017
124
cited
Thompson Sampling for the MNL-Bandit
Annual Conference Computational Learning Theory · 2017
103
cited
An efficient algorithm for contextual bandits with knapsacks, and an extension to concave objectives
Annual Conference Computational Learning Theory · 2015
96
cited
On Addressing Efficiency Concerns in Privacy-Preserving Mining
International Conference on Database Systems for Advanced Applications · 2003
72
cited
Learning in Structured MDPs with Convex Cost Functions: Improved Regret Bounds for Inventory Management
ACM Conference on Economics and Computation · 2019
67
cited
Correlation robust stochastic optimization
ACM-SIAM Symposium on Discrete Algorithms · 2009
55
cited
A Near-Optimal Exploration-Exploitation Approach for Assortment Selection
ACM Conference on Economics and Computation · 2016
52
cited
Sotabase
Shipra Agrawal | Researcher Profile | Sotabase | Sotabase