Gavin Brown

About

Hello! I am a fourth-year Computer Science PhD student at Boston University. I am advised by Adam Smith. I received a BS in Mathematics from Case Western Reserve University in 2015.

My research focuses on the theory of machine learning and data privacy. I am interested in creating algorithms for differentially private learning and statistics as well as understanding the necessity of memorization in machine learning.

Download my CV (pdf)

Publications

G. Brown, M. Gaboardi, A. Smith, J. Ullman, L. Zakynthinou. "Covariance-Aware Private Mean Estimation Without Private Covariance Estimation." In submission. arXiv.

G. Brown, M. Bun, V. Feldman, A. Smith, K. Talwar, "When Is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?" STOC 2021. arXiv. Proceedings version.

G. Brown, I. Kalemaj, S. Hod, "Performative prediction in a stateful world." NeurIPS Workshop on Consequential Decision Making in Dynamic Environments, 2020. arXiv.

L. Jensen, G. Brown, X. Wang, J. Harer, S. Chin, "Deep learning for Minimal Context Classification of Block-types through Side-Channel Analysis", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4196.

X. Wang, Q. Zhou, J. Harer, G. Brown, S. Qiu, Z. Dou, J. Wang, A. Hinton, C. A. Gonzalez, S. P. Chin. Deep learning-based classification and anomaly detection of side-channel signals. Cyber Sensing. 2018.

S. P. Chin, J. Cohen, A. Albin, M. Hayvanovych, E. Reilly, G. Brown, and J. Harer. "A Mathematical Analysis of Network Controllability Through Driver Nodes." IEEE Transactions on Computational Social Systems 4, no. 2 (2017): 40:51.

J. Miao, G. Brown, and P. Taylor. "Theoretically guided design of efficient polymer dielectrics." Journal of Applied Physics 115.9 (2014): 094104.

Presentations

Penn State University Statistical Data Privacy Seminar. "When Is Memorization of Entire Examples Necessary for High-Accuracy Learning?" Talk. 2021

Hebrew University Theory Seminar. "When Is Memorization of Entire Examples Necessary for High-Accuracy Learning?" Talk. 2021

Workshop on the Theory of Overparameterized Machine Learning 2021. "When Is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?" Lightning talk.

Boston University Probability and Statistics Seminar. "When Is Memorization of Entire Examples Necessary for High-Accuracy Learning?" Talk. 2021.

Google Differential Privacy Workshop 2021. "When Is Memorization of Entire Examples Necessary for High-Accuracy Learning?" Poster presentation.

Teaching

CS 537 - Randomness in Computing (Sofya Raskhodnikova). Graduate Class. Spring 2020. Teaching Fellow.

CS 330 - Introduction to Algorithms (Adam Smith and Dora Erdos). Undergraduate Class. Fall 2019. Teaching Fellow.

CS 542 - Machine Learning (Peter Chin). Graduate Class. Summer 2019, Session I. Teaching Fellow.

CS 112 - Introduction to Computer Science II (Christine Papadakis-Kanaris). Undergraduate Class. Fall 2018. Teaching Fellow.

CS 542 - Machine Learning (Peter Chin). Graduate Class. Spring 2018. Teaching Fellow.