picture of me taken by Sury.

Daniel G. Alabi

Instructor, NaijaCoder
Junior Fellow, Simons Society of Fellows
Postdoctoral Researcher, Computer Science and Data Science, Columbia University
Postdoctoral Host: Daniel Hsu
alabid [at] cs [dot] columbia [dot] edu
Photo credit: My neighbor Sury @scrodcity

Research Overview

In general, through the use of (mostly) mathematical tools, I study the limits and capabilities of statistics for computer science applications. Currently, I am particularly interested in understanding the limits of performing computational social science under different constraints. e.g., for learning with limited resources or with privacy. I am also interested in other areas in the general fields of statistics, probability, machine learning, and theoretical computer science.

Selected Papers

Differentially Private Simple Linear Regression
with Audra McMillan, Jayshree Sarathy, Adam Smith, and Salil Vadhan
Proceedings of the Journal on Privacy Enhancing Technologies (PoPETs), 2022  [arxiv]  [PETS] 
Learning to Prune: Speeding up Repeated Computations
with Adam Tauman Kalai, Katrina Ligett, Cameron Musco, Christos Tzamos, and Ellen Vitercik
Proceedings of the Conference on Learning Theory (COLT), 2019  [arxiv]  [PMLR] 
Unleashing Linear Optimizers for Group-Fair Learning and Optimization
with Nicole Immorlica and Adam Tauman Kalai
Proceedings of the Conference on Learning Theory (COLT), 2018  [arxiv]  [PMLR] 
Learning Certifiably Optimal Rule Lists for Categorical Data
with Elaine Angelino, Nicholas Larus-Stone, Margo Seltzer, and Cynthia Rudin
Proceedings of the Journal of Machine Learning Research (JMLR), 2018  [arxiv]  [JMLR] 
See all papers here.

Selected Code Artifacts

Collaborative LaTeX Editor
CORELS is a custom discrete optimization technique for building decision/rule lists over a categorical feature space.
See my GitHub page for some more code artifacts not listed here.