picture of me in Milan, Italy.

Daniel Alabi

alabid [at] g [dot] harvard [dot] edu

I am a Ph.D. student in the Theory of Computation group at Harvard University, where I am advised by Salil Vadhan. I'm also affiliated with the Harvard Privacy Tools project.

My research interests lie in theoretical computer science (algorithms & complexity theory) with a current focus on problems in the following areas: data privacy, theoretical machine learning, and quantum computation.

In my free (and not-so-free) time, I participate in ballroom activities as a member of Harvard's Competitive Ballroom Dance Team.

Funding Acknowledgements: My research was/is supported by Harvard SEAS, Harvard CRCS, the Facebook Emerging Scholar Award, and the Courtlandt S. Gross Memorial Scholarship.

Research Papers

Learning to Prune: Speeding up Repeated Computations.
with Adam Tauman Kalai, Katrina Ligett, Cameron Musco, Christos Tzamos, and Ellen Vitercik.
COLT, June, 2019  [arxiv] 
Unleashing Linear Optimizers for Group-Fair Learning and Optimization.
with Nicole Immorlica and Adam Tauman Kalai.
COLT, July, 2018  [arxiv]  [PMLR] 
Learning Certifiably Optimal Rule Lists for Categorical Data.
with Elaine Angelino, Nicholas Larus-Stone, Margo Seltzer, and Cynthia Rudin.
JMLR, June, 2018  [arxiv]  [JMLR] 
Long Journal Version of KDD 2017, SysML 2018 papers with more analyses/results/experiments/proofs.
Systems Optimizations for Learning Certifiably Optimal Rule Lists.
with Elaine Angelino, Vassilios Kaxiras, Nicholas Larus-Stone, Aditya Saligrama, Margo Seltzer, and Cynthia Rudin.
SysML, February, 2018  [pdf] 
Learning Certifiably Optimal Rule Lists.
with Elaine Angelino, Nicholas Larus-Stone, Margo Seltzer, and Cynthia Rudin.
KDD, August, 2017  [pdf] 
PFunk-H: Approximate Query Processing using Perceptual Models.
with Eugene Wu.
Proceedings of the International Workshop on Human-in-the-Loop Data Analytics (HILDA), June, 2016 
Poster at North East Database Day, January, 2016.

Selected Projects (with Code Artifacts)

FlyLaTeX
Collaborative LaTeX editor.
CORELS
CORELS is a custom discrete optimization technique for building rule lists over a categorical feature space.
See my GitHub page for some more projects not listed here.

Teaching

Check out some of my instructional worksheets.