Gaurav Sinha

Microsoft Research E-mail: sinhagaur88 AT gmail(dot)com

About Me

I am a Principal Researcher at Microsoft Research, working in the areas of Reinforcement Learning, Causal Inference and Theory. I received my Ph.D. in Mathematics from the California Institute of Technology in 2016, where I was advised by Prof. Eric Rains and my Integrated M.Sc. in Mathematics and Scientific Computing from Indian Institute of Technology (IIT) Kanpur in 2011.

Research Interests

• Reinforcement Learning

• Causal Inference and Discovery

• Information Retrieval

• Theoretical Computer Science

Selected Papers (View all)

• Learning good interventions in causal graphs via covering
  Joint with Ayush Sawarni, Rahul Madhavan and Siddharth Barman
  UAI 2023, PMLR

• Combinatorial categorized bandits with expert rankings
  Joint with Sayak Ray Chowdhury, Nagarajan Natarajan and Amit Sharma
  UAI 2023, PMLR

• Efficient Convex Exploration for Minimizing Simple Regret in Layered Causal MDPs
  Joint with Rahul Madhavan, Aurghya Maiti and Siddharth Barman
  ArXiv, Submitted

• A Causal Bandit Approach to Learning Good Atomic Interventions in Presence of Unobserved Confounders
  Joint with Aurghya Maiti and Vineet Nair
  UAI 2022, ArXiv
  

• Almost Optimal Universal Lower Bound for Learning Causal DAGs with Atomic Interventions
  Joint with Vibhor Porwal and Piyush Srivastava
  AISTATS 2022 (Oral), ArXiv
  

• Efficient reconstruction of depth three circuits with top fan-in two
  ITCS 2022, ArXiv, ECCC
  

• Disentangling Mixtures of Unknown Causal Interventions
  Joint with Abhinav Kumar
  UAI 2021 (Oral)
  

• Budgeted and Non-Budgeted Causal Bandits
  Joint with Vineet Nair and Vishakha Patil
  AISTATS 2021, ArXiv
  

• Reconstruction of Real depth-3 Circuits with top fan-in 2
  CCC 2016, ArXiv, ECCC
  

Professional Service

• Reviewer: NeurIPS 2023, AISTATS 2023, KDD 2023, ICML 2022, AISTATS 2022, CODS-COMAD 2022, STOC 2021, AISTATS 2021
  

• PC Member: CODS-COMAD 2022

• Online Chair: CLeaR 2024