Running simulations on compute clusters with Kubernetes and Slurm, using clingo to solve answer-set programming formulation, establishing use on empirical data, and implementing causal learning methods to optimize inputs
In many common fairness settings, we can’t observe counterfactuals — e.g. would a person we denied a loan pay it back if we had granted it? — and this biases training data, creating uncertainty particularly for groups historically denied loans. Using techniques like structural equation modeling and infomax active learning, we show how in these situations even with optimal, unbiased models, differences in true group parameters can lead to large differences in uncertainty.
Technically, using blavaan for Bayesian latent-variable modeling, and formulated a maximum-likelihood problem to find points with greatest informational value
Used ML tools such as DeepLabCut and B-SOID on remote compute cluster, extracting pose information from mouse behavior video
Performed timeseries manipulation and analysis
Worked on projects studying neurological underpinnings of physiological arousal, mouse scent marking, and olfaction
Research Intern, UC San Diego Computer Science and Engineering
June 2021 — December 2021
Under Professor Christine Alvarado, studied the effects of ERSP, an early-undergraduate CS research program, on students’ senses of identity as researchers and computer scientists
Used thematic analysis methods on open-ended survey data, as well as Python for preprocessing, analysis, and interrater reliability calculation
Qualcomm Institute Learning Academy
September 2020 — December 2021
Along with another undergraduate, supervised by Leanne Chukoskie at the Qualcomm Institute at UCSD, conducted self-directed research project on engagement in online learning during COVID pandemic
Developed and distributed survey of UCSD students about their course experiences
Analyzed and visualized data in R, wrote most of paper’s Results section
Published in Frontiers in Education as co-first author
📝 Publications
ION-C: Integration of Overlapping Networks via Constraints.Nair, P., Bhandari, P., Abavisani, M., Plis, S., & Danks, D. (2024). arXiv preprint arXiv:2411.04243. https://arxiv.org/abs/2411.04243
Active Learning and Epistemic Defenses of Fairness.Nair, P. (2024). (Master’s thesis, University of California, San Diego). Available on escholarship.org.