Publications

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

• 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

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

• Multi-touch Attribution for complex B2B customer journeys using Temporal Convolutional Networks
  Joint with Aniket Agrawal, Nikhil Sheoran and Sourav Suman
  TempWeb 2022, 12th Temporal Web Analytics Workshop, The Web Conference 2022
  

• 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
  

• Dis-entangling Mixture of Interventions on a Causal Bayesian Network Using Aggregate Observations
  Joint with Ayush Chauhan, Aurghya Maiti, Naman Poddar and Pulkit Goel
  StarAI 2020, Ninth International Workshop on Statistical Relational AI, AAAI 2020, ArXiv
  

• SparTun : Sparse Grid Tuning in Computational Advertising
  Ampere 2018, Bing Ads, Microsoft

• Blackbox Reconstruction of Depth Three Circuits with Top Fan-in Two
  Ph.D. Thesis, California Institute of Technology
  

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

• Multiple point evaluation on combined tensor product supports
  Joint with Ralf Hiptmair and Gisela Philips
  Numerical Algorithms 2012 (2), 317-337, ETH Zurich Research Collection
  

• JSZap: Compressing JavaScript Code
  Joint with Martin Burtscher, Benjamin Livshits and Benjamin Zorn
  USENIX WebApps 2010, Microsoft Technical Report