Bio


Kiran Shiragur is a final year PhD student at Stanford, co-advised by Prof. Moses Charikar and Prof. Aaron Sidford. His research interests lie in the intersection of theoretical computer science, statistics, information theory and optimization. A major theme of his work involves building efficient algorithms for extracting information from limited data. Complementary to this theme, he also enjoy formulating new mathematical models and practical solutions for problems in the natural and social sciences, that lie beyond the range of traditional machinery.

RESEARCH AREA: Operations Research, Theoretical Computer Science

All Publications


  • Reward Identification in Inverse Reinforcement Learning Kim, K., Garg, S., Shiragur, K., Ermon, S., Meila, M., Zhang, T. JMLR-JOURNAL MACHINE LEARNING RESEARCH. 2021
  • Efficient Profile Maximum Likelihood for Universal Symmetric Property Estimation Charikar, M., Shiragur, K., Sidford, A., Charikar, M., Cohen, E. ASSOC COMPUTING MACHINERY. 2019: 780–91
  • A General Framework for Symmetric Property Estimation Charikar, M., Shiragur, K., Sidford, A., Wallach, H., Larochelle, H., Beygelzimer, A., d'Alche-Buc, F., Fox, E., Garnett, R. NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2019