Jordan Awan

Bio

I studied at Clarion University from 2011-2014, earning a B.S. in Mathematics. After this, I completed a M.A. in Mathematics at Brandeis University in 2016 under the advisement of Dr. Olivier Bernardi. In May of 2020, I completed my Ph.D. in Statistics at Penn State University, advised by Dr. Aleksandra Slavkovic and Dr. Matthew Reimherr. Currently I am an Assistant Professor of Statistics at Purdue University. I also work as a differential privacy consultant for the federal non-profit, MITRE.

Research Interests

My primary research interest is in data privacy, where the goal is to publish meaningful statistical results on sensitive datasets, without compromising the privacy of the participants in the dataset. In particular, I mostly work in the framework of differential privacy, which has been adopted by a number of tech companies as well as the US Census. Some data privacy problems that I am particularly interested in are 1) performing valid statistical inference subject to privacy constraints (e.g., confidence intervals, hypothesis tests, posterior inference), 2) designing privacy-aware algorithms for a variety of tasks (e.g., functional data analysis, topological data analysis), and 3) foundations of data privacy (e.g., definitions of privacy, optimizing basic privacy mechanisms)

I also work with a variety of scientists as an applied Statistician on problems related to 1) diagnosing and treating voice disorders, 2) developing novel methods of low-cost spirometry, and 3) studying the basic laws of physics.

Before transitioning to Statistics, I worked on dicrete mathematics problems in graph theory, matroid theory, and discrete geometries.

News

• Book chapter, "Statistical Inference and Differential Privacy," in Handbook of Sharing Confidential Data,
• General audience article, Here's How Machine Learning can Violate your Privacy.
• "Simulation-based Finite-sample Inference for Privatized Data" was accepted for publication at JASA.
• "Optimizing Noise for f-Differential Privacy via Anti-Concentration and Stochastic Dominance" was accepted for publication at JMLR.
• New preprints
  • Eng, K., Awan, J., Ju, N., Rao, V., Gong, R. "dapper: Data Augmentation for Private Posterior Estimation in R."
  • Cho, Y., Awan, J. "Formal Privacy Guarantees with Invariant Statistics" arXiv:2410.17468.
  • Ohnishi, Y., Awan, J. ''Differentially Private Covariate Balancing Causal Inference" arXiv:2410.14789.
  • Awan, J., Edwards, A., Bartholomew, P., Sillers, A. ''Best Linear Unbiased Estimate from Privatized Histograms." arXiv:2409.04387.
  • Awan, J., Barrientos, A. F., Ju, N. ''Statistical Inference for Privatized Data with Unknown Sample Size.'' arXiv:2406.06231.

Selected Publications

• Awan, J., Wang, Z. (2024) ''Simulation-based Finite-sample Inference for Privatized Data.'' Journal of the American Statistical Association.
• Kang, T., Kim, S., Sohn, J., Awan, J. (2024) ''Differentially Private Topological Data Analysis.'' Journal of Machine Learning Research.
• Awan, J., Vadhan, S. (2023) ''Canonical Noise and Private Hypothesis Tests with Applications to Difference of Proportions Testing.'' Annals of Statistics.
• Awan, J., Dong, J. (2022) ''Log-Concave and Multivariate Canonical Noise Distributions for Differential Privacy.'' Advances in Neural Information Processing Systems 36.
• Ju, N., Awan, J., Gong, R., Rao, V. (2022) ''Data Augmentation MCMC for Bayesian Inference from Privatized Data.'' Advances in Neural Information Processing Systems 36.
• Awan, S., Awan, J. (2022) ''Use of a Vortex Whistle for Measures of Respiratory Capacity.'' Journal of Voice. Best paper award.
• Awan, J., Slavkovic, A. (2021) ''Structure and Sensitivity in Differential Privacy: Comparing K-Norm Mechanisms.'' Journal of the American Statistical Association.
• Awan, J., Bernardi, O. (2020) ''Tutte Polynomials for Directed Graphs.'' Journal of Combinatorial Theory, Series B.
• Awan, J., Kenney, A., Reimherr, M., Slavkovic A. (2019) ''Benefits and Pitfalls of the Exponential Mechanism with Applications to Hilbert Spaces and Functional PCA.'' Proceedings of the 36th International Conference on International Conference on Machine Learning.
• Awan, J., Slavkovic, A. (2018) ''Differentially Private Uniformly Most Powerful Tests for Binomial Data.'' Advances in Neural Information Processing Systems 31.

All publications