|
Justin Whitehouse
Email: jwhiteho (at) andrew (dot) cmu (dot) edu
CV: click here
|
I am a third year PhD student in the Computer Science Department
at Carnegie Mellon University. I am currently co-advised by Aaditya Ramdas and Steven Wu. I work at the intersection of statistics, machine learning, and differential privacy. In particular, I am interested in developing algorithms which allow data analysts to flexibly work with private data.
Before working in the above areas, I studied problems in stochastic scheduling and queueing with Mor Harchol-Balter and Weina Wang. In particular, we developed optimal algorithms for scheduling parallelizable jobs in multiserver systems.
Before coming to Carnegie Mellon, I was an undergraduate at Columbia University in New York City. There, I majored in mathematics and computer science. I was fortunate enough to be advised by Allison Bishop and Suman Jana .
Publications and Preprints
- A Tradeoff Between Privacy and Accuracy: Noise Reduction via Brownian Motion
(with Aaditya Ramdas, Steven Wu, and Ryan Rogers).
In Progress.
- Improved Privacy Filters and Odometers: Time-Uniform Bounds in Privacy Composition
(with Aaditya Ramdas, Steven Wu, and Ryan Rogers).
Theory and Practice of Differential Privacy (TPDP), 2021.
- The Case for Phase-Aware Scheduling of Parallelizable Jobs
(with Benjamin Berg, Benjamin Moseley, Mor Harchol-Balter, and Weina Wang).
39th International Symposium on Computer Performance, Modeling, Measurements and Evaluation, 2021.
- Optimal Resource Allocation for Elastic and Inelastic Jobs
(with Benjamin Berg, Benjamin Moseley, Mor Harchol-Balter, and Weina Wang).
ACM Symposium on Parallelism in Algorithms and Architectures (SPAA 2020).
-
Bringing Engineering Rigor to Deep Learning
(with Kexin Pei, Shiqi Wang, Yuchi Tian, Carl Vondrick, Yinzhi Cao, Baishakhi Ray, Suman Jana, and Junfen Yang).
ACM SIGOPS Operating Systems Review, Volume 53 Issue 1 (SIGOPS 2019).
-
Efficient Formal Safety Analysis of Neural Networks
(with Shiqi Wang, Suman Jana, Kexin Pei, and Junfeng Yang).
Advances in Neural Information Processing Systems (Neurips 2018).
-
Formal Security Analysis of Neural Networks Using Symbolic Intervals
(with Shiqi Wang, Suman Jana, Kexin Pei, and Junfeng Yang).
27th USENIX Security Symposium, 2018.
Teaching
I was a teaching assistant for the following courses at Columbia University.
- Computer Science Theory (Spring 2019).
- Modern Algebra II (Spring 2019).
- Complexity Theory (Fall 2018).
- Introduction to Cryptography (Fall 2018).
- Number Theory and Cryptography (Spring 2018).