Cheryl Flynn Brooks


Principal Inventive Scientist
AT&T Data Science & AI Research
Bedminster, NJ
flynn (dot) cheryl (at) gmail (dot) com

Full CV

About Me

I am a statistics and data science researcher for the AT&T Chief Data Office. I am interested in problems related to fairness and ethics in data science, data privatization, network modeling, model selection, and unsupervised learning.

I received my PhD in Statistics from New York University in 2014 under the supervision of Cliff Hurvich, Patrick Perry, and Jeff Simonoff.

Prior to that I received my BA in Economics and Mathematics from McGill University.


Brito, F. T., Farias, V. A. E., Flynn, C., Majumdar, S., Machado, J. C., and Srivastava, D. Global and Local Differentially Private Release of Count-Weighted Graphs. Submitted.

Flynn, C., Guha, A., Majumdar, S., Srivastava, D., and Zhou, Z. Towards Algorithmic Fairness in Space-Time: Filling in Black Holes. NeurIPS 2022 TSRML Workshop, 2022.

Majumdar, S., Flynn, C., and Mitra, R. Detecting Bias in the Presence of Spatial Autocorrelation. NeurIPS 2021 AFCR Workshop, PMLR 171: 6-18, 2022.

Dodwell, E., Flynn, C., Krishnamurthy, B., Majumdar, S., and Mitra, R. System to Integrate Fairness Transparently: An Industry Approach. arXiv:2006.06082, 2020.

Farias, V., Brito, F., Flynn, C., Machado, J., Majumdar, S., and Srivastava, D. Local Dampening: Differential Privacy for Non-numeric Queries via Local Sensitivity. PVLDB, 14(4): 521-533, 2020.

Flynn, C. and Perry, P. Profile Likelihood Biclustering. Electronic Journal of Statistics, 14(1):731-768, 2020. [GitHub]

Li, R., Jian, J., Ju, C., Flynn, C., Hsu, W., Wang, J., Wang, W., and Xu, T. Enhancing Response Generation Using Chat Flow Identification. KDD Workshop on Conversational AI, 2018.

Xi, H., Machanavajjhala, A., Flynn, C., and Srivastava, D. Composing Differential Privacy and Secure Computation: A case study on scaling private record linkage. In Proceedings of the ACM Conference on Computer and Communications Security, 2017.

Flynn, C., Hurvich, C., and Simonoff, J. S. On the Sensitivity of the Lasso to the Number of Predictor Variables. Statistical Science, 32(1): 88-105, 2017.

Flynn, C., Shirley, K., and Wang, W. Deconstructing Domain Names to Reveal Latent Topics. In Proceedings of the IEEE International Conference on Data Science and Advanced Analytics, 2016.

Flynn, C., Hurvich, C. M., and Simonoff, J. S. Discussion: Deterioration of performance of the lasso with many predictors. Statistical Modelling, 16:212-216, 2016.

Flynn, C., Hurvich, C., and Simonoff, J. Efficiency for Regularization Parameter Selection in Penalized Likelihood Estimation of Misspecified Models. Journal of the American Statistical Association, 108(503):1031-1043, 2013.