Richa Rastogi

[Google Scholar]

Hi! I'am a Computer Science PhD Student at Cornell University and I'am very fortunate to be advised by Professor Thorsten Joachims.
My research interests lie at the intersection of machine learning, optimization and algorithms. Specifically, I work on questions relating to dynamics, uncertainties and fairness in machine learning systems.

Prior to starting PhD, I spent several years working as a Data Scientist at Amazon Advertising and as a Controls Software Engineer at Amazon Fullfillment Technologies, where I developed software for deployment in production systems. Prior to that, I completed a Masters in Industrial Engineering and Operations Research at ISyE, Georgia Tech and a Bachelors of Engineering at Delhi University, India.

News

  • 08/24: Our paper, Fairness in Ranking under Disparate Uncertainty is accepted at ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO'24). See you in Mexico!
  • 07/24: I will be at the Grace Hopper Celebration of Women in Computing in Philadelphia. Come stop by the Cornell booth to chat !
  • 06/24: Short version of our paper MultiScale Policy Learning for Alignment with Long Term Objectives is accepted at the ICML Models of Human Feedback for AI Alignment workshop. See you in Vienna!
  • 08/23: Presented our paper, Fairness in Ranking under Disparate Uncertainty, as a Spotlight (Oral) at UAI workshop on Epistemic AI at CMU, Pittsburgh! We introduce Equal-Opportunity Ranking (EOR) as a new fairness criterion for ranking that provably reduces the group unfairness induced when the uncertainty of the underlying relevance model differs between groups of candidates.
  • 01/23: Our paper, Semi-Parametric Inducing Point Networks and Neural Processes, is accepted at International Conference on Learning Representations (ICLR '23)! We introduce semi-parametric inducing point networks (SPIN), a general-purpose architecture that can query the training set at inference time in a compute-efficient manner.
  • 08/21: Our Patent filed on behalf of Amazon is granted by USPTO! It describes a closed loop feedback dynamical system with online updates for accurately positioning labels on moving packages.

Selected Papers

My full list of papers and patents are here.

Fairness in Ranking under Disparate Uncertainty
Richa Rastogi , Thorsten Joachims.
ACM Conference on on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO'24), ICML Workshop on Humans, Algorithmic Decision-Making and Society, 2024, Spotlight (Oral) at UAI Workshop on Epistemic AI, 2023
code poster

Semi-Parametric Inducing Point Networks and Neural Processes
Richa Rastogi , Yair Schiff, Alon Hacohen, Zhaozhi Li, Ian Lee, Yuntian Deng, Mert R Sabuncu, Volodymyr Kuleshov.
International Conference on Learning Representations (ICLR'23)
code