About me

I am a Research Scientist at Meta, working on data sub-sampling algorithms for Facebook Ads. Previously, I obtained my PhD in Computer Science (Machine Learning) at UMass Amherst; my PhD research was on improving data selection efficiency with differentiable optimization layers. During my PhD, I won the NeurIPS 2020 education challenge for improving question selection efficiency in computerized adaptive tests (e.g., GRE, GMAT). During my PhD, I did two research internships at Adobe Research, where I worked on optimal bidding strategy in real-time bidding systems. Before my PhD, I was a Software Engineer (Applied Scientist) at Microsoft BingAds where I had the opportunity to work on improving click performance and ad selection algorithms. Even before that, I had amazing years at the Indian Institute of Science, Bangalore (IISc), where I worked on robust learning under noisy labels. I have been fortunate to work with some amazing researchers and publish in many exciting machine learning/data mining conferences and workshops such as AAAI, CVPR, ICML, IJCAI, KDD, and SIAM SDM. I also received the Best Student Paper Award from the IEEE Big Data (2020) conference.

Research Interest

  • Meta Learning, Differentiable Optimization Layers, Bi-level Optimization
  • Sequential Models, Reinforcement Learning, Inverse Reinforcement Learning
  • Computational Advertising, Computer Vision, NLP, AI for Social Goods


  • Sep 2022: joined Meta as Research Scientist.
  • Aug 2022: successfully defended my PhD thesis.
  • Jan 2022: our team was among the grand prize winners in NAEP Automated Scoring Challenge. Check it out here.
  • Dec 2021: paper on Differentiable Sketching in Recommender Systems has been accepted at AAAI 2022 (15% (1349/9020) Acceptance rate!).
  • Nov 2021: honored to receive 2021 Duolingo Dissertation Award.
  • Apr 2021: paper on computerized adaptive testing under bilevel framework has been accepted at IJCAI 2021 (13.9% Acceptance rate!).
  • Apr 2021: paper on learning with noisy labels with contrastive initialization to appear at LLID Workhop at CVPR 2021.
  • Dec 2020: honored to get the Best Student Paper Award at IEEE Big Data 2020.
  • Nov 2020: won the personalized question selection task in NeurIPS 2020 Education Challenge. Implementation is publicly available.
  • Nov 2020: paper on robust sample reweighting strategy without gold samples to appear at WACV 2021. Paper/codes will be released soon.
  • Nov 2020: paper on optimal career trajectory modeling to appear at IEEE Big Data 2020. Paper/codes will be released soon.
  • Sep 2020: will be serving as Program committee member for AAAI 2021 and WACV 2021 .
  • Aug 2020: selected for KDD 2020 Student Award!
  • May 2020: paper on knowledge tracing to appear at KDD 2020. Paper/codes/data will be released soon.
  • Mar 2020: selected for SIAM SDM Student Travel Award.
  • Dec 2019: paper on optimal bidding strategy to appear at SIAM SDM 2020.
  • May 2019: paper on point processes to appear at ICML Time series workshop 2019.
  • May 2019: will be joining Adobe Research, San Jose for internship (again).
  • Sep 2018: had a great summer at Adobe Research, San Jose.
  • Aug 2017: last day at Microsoft!
  • Jul 2017: will be joining UMass Amherst for PhD in Computer Science.
  • Feb 2017: paper on robust loss functions for deep networks to appear at AAAI 2017.