About Me

My primary research spans differential privacy and machine unlearning.

I am also excited about theory-driven continual and sequential learning.

I am working under the guidance of Mark Bun in the Theoretical Computer Science research group.

Service

• Founder, BU ACM-ICPC Team (2020)
• Co-President, SIAM BU Student Chapter

- organizes graduate student and faculty talks on ML, Dynamics, Graphs at the BU SIAM seminar series

Projects (listed)

Privacy Preserving Machine Learning| Differential Privacy, Learning Theory

• The broadest goal is to better understand the divide between traditional and private approaches in interpretable decision-making and convert private learning algorithms from the batch setting to the online setting.

• Developed near-optimal differentially private learning algorithms in the batch (PAC) and online settings for foundational concept classes such as generalized decision lists, sparse disjunctions, and large-margin halfspaces.

Responsible & Safe AI | Machine Unlearning, Computer Vision, XAI

• Developed a dual-objective approximate machine unlearning algorithm for Image classification (NeurIPS 2023 Machine Unlearning Challenge).

• Experimented with other unlearning methods (i.e. SCalable Remembering and Unlearning unBound (SCRUB), teacher-student, negative gradient descent, and variants with relative entropy regularization) on CIFAR-10.

• Graphical Models (on pause)

Template by Kira Goldner©