Daniel Alabi
alabid [at] g [dot] harvard [dot] edu
Harvard University
Advised by Salil Vadhan
Ph.D. student in the
Theory of Computation group
and the Harvard Privacy Tools group
In particular, I'm interested in the tradeoffs in computational and statistical resources that result when we require provable guarantees (e.g., for privacy) on statistical models and machine learning predictors. Example computational resources include time, memory, randomness, communication, and parallelism. Example statistical resources include samples (or labeled examples for classification or regression) drawn from an unknown distribution.
Personal: I am Nigerian and a member of Harvard's
Selected Research
- Differentially Private Simple Linear Regression
- with Audra McMillan, Jayshree Sarathy, Adam Smith, and Salil Vadhan
- [arxiv]
- Learning to Prune: Speeding up Repeated Computations
- with Adam Tauman Kalai, Katrina Ligett, Cameron Musco, Christos Tzamos, and Ellen Vitercik
- COLT, 2019 [arxiv] [PMLR]
- Unleashing Linear Optimizers for Group-Fair Learning and Optimization
- with Nicole Immorlica and Adam Tauman Kalai
- COLT, 2018 [arxiv] [PMLR]
- Learning Certifiably Optimal Rule Lists for Categorical Data
- with Elaine Angelino, Nicholas Larus-Stone, Margo Seltzer, and Cynthia Rudin
- JMLR, 2018 [arxiv] [JMLR]
- FlyLaTeX
- Collaborative LaTeX Editor
- CORELS
- CORELS is a custom discrete optimization technique for building rule lists over a categorical feature space.
- Teaching Fellow, Algorithms at the End of the Wire (CS 222), Harvard, Fall 2020
- Teaching Fellow, Algorithms & Data Structures (CS 124), Harvard, Spring 2018
- Teaching Assistant, Data Structures (CS 201), Carleton College, Winter & Spring 2014
- Teaching Assistant, Intro to Computer Science (CS 111), Carleton College, Fall 2013
See all papers here.