• Accepted paper in SIGMOD 2021.
    Our demonstration paper on "Demonstrating UDO: A Unified Approach for Optimizing Transaction Code, Physical Design, and System Parameters via Reinforcement Learning" with Immanuel Trummer and Junxiong Wang is selected for SIGMOD 2021..
  • Our paper on "Deep Learning for Deep Waters: An Expert-in-the-Loop Machine Learning Framework for Marine Sciences" is published in JMSE, February 2021 issue. The paper is accessible at this link.
  • Accepted paper in AAAI 2021 on Verifying Fairness using Stochastic SAT Solvers.
    We (with Bishwamittra Ghosh and Kuldeep S. Meel) have proposed a stochastic SAT based approach Justicia to verify fairness of machine learning models. It comes with both experimental scalability and theoretical error bound unlike the existing formal verifiers of group fairness. The preprint is available at:
  • Accepted paper in proccedings of ICBINB workshop at NeurIPS 2020.
    Our paper on "Inferential Induction: A Novel Framework for Bayesian Reinforcement Learning" with Christos Dimitrakakis, Emilio Jorge, Hannes Eriksson, and Divya Grover is selected for ICBINB@NeurIPS. It is available in Proccedings of Machine Learning Research (PMLR)..
  • Our paper on "Privacy in Multi-armed Bandits: Fundamental Definitions and Lower Bounds on Regret" with Christos Dimitrakakis is selected for PPML-PriML 2020. The detailed version is available at:
  • Our paper on "Differential Privacy at Risk: BridgingRandomness and Privacy Budget" with Ashish Dandekar and Stéphane Bressan is selected for Issue 1 of PoPETS, 2021. Check the final version here.
  • Appreciation as a top reviewer in ICML 2020.

Open Positions

  • PhD
    Topic: Learning to Adaptively Attack and Defend Privacy of Machine Learning Systems (Job Description).
    We are looking for a PhD student willing to join the project “Learning to Adaptively Attack and Defend Privacy of Machine Learning Systems”. This topic is at the intersection of reinforcement learning and differential privacy. The candidate will be supported by AI_PhD@Lille grant, and supervised by D. Basu and Philippe Preux of Scool team at Inria Lille- Nord Europe. Tenure of the PhD candidacy is three years. The candidate is expected to join on 1st September, 2021. Application is open till 15th April, 2021.

    The PhD position is now closed but we have internship positions on privacy, fairness, and RL theory. Email me if you are interested!