Jess Sorrell (original) (raw)
Jessica Sorrell
Assistant Professor
Department of Computer Science
Johns Hopkins University
jess@jhu.edu
Research. I'm broadly interested in the theoretical foundations of responsible computing, particularly questions related to fairness, privacy, robustness, and reproducibility. I also work on problems in lattice-based cryptography, with a focus on secure computation.
About me. I'm new faculty at Johns Hopkins as of July, 2024. Before that, I was a postdoc at the University of Pennslyvania, working with Aaron Roth and Michael Kearns. I completed my PhD in Computer Science at the University of California, San Diego, advised by Daniele Micciancio and Russell Impagliazzo. I did my undergrad in Applied Mathematics at the Rochester Institute of Technology.
Publications and Manuscripts
Oracle Efficient Reinforcement Learning for Max-Value Ensembles
Marcel Hussing, Michael Kearns, Aaron Roth, Sikata Sengupta, Jessica Sorrell
NeurIPS 2024
Replicable Reinforcement Learning
Eric Eaton, Marcel Hussing, Michael Kearns, Jessica Sorrell
NeurIPS 2023
Stability is Stable: Connections between Replicability, Privacy, and Adaptive Generalization
Mark Bun, Marco Gaboardi, Max Hopkins, Russell Impagliazzo, Rex Lei, Toniann Pitassi, Satchit Sivakumar, Jessica Sorrell
STOC 2023
Multicalibration as Boosting for Regression
Ira Globus-Harris, Declan Harrison, Michael Kearns, Aaron Roth, Jessica Sorrell
ICML 2023
Securing Approximate Homomorphic Encryption Using Differential Privacy
Baiyu Li, Daniele Micciancio, Mark Schultz, Jessica Sorrell
Crypto 2022
Reproducibility in Learning
Russell Impagliazzo, Rex Lei, Toniann Pitassi, Jessica Sorrell
STOC 2022
Boosting in the Presence of Massart Noise
Ilias Diakonikolas, Russell Impagliazzo, Daniel Kane, Rex Lei, Jessica Sorrell, Christos Tzamos
COLT 2021
Simpler Statistically Sender Private Oblivious Transfer from Ideals of Cyclotomic Integers
Daniele Micciancio, Jessica Sorrell
Asiacrypt 2020
Efficient, Noise-Tolerant, and Private Learning via Boosting
Mark Bun, Marco Leandro Carmosino, Jessica Sorrell
COLT 2020
The Fiat-Shamir Zoo: Relating the Security of Different Signature Variants
Matilda Backendal, Mihir Bellare, Jessica Sorrell, Jiahao Sun
NordSec 2018
Ring Packing and Amortized FHEW Bootstrapping
Daniele Micciancio, Jessica Sorrell
ICALP 2018
Teaching
- Spring 2025. Theory of Replicable Machine Learning (EN.601.774)
Interests
In my free time, I enjoy aerial silks and attempting to walk my cat.
