Ongoing
Interpretable Differentially Private Continual Learning with Prototype-Based Classifiers
Prototype-based classification for interpretable continual learning under differential privacy. Submitted to ICLR.
ResearchIdeas in progress,
Ideas in progress,
results in print.
Work across differential privacy, Bayesian inference, continual learning, and foundation models for tabular data.
01 projects
Ongoing work
Questions and methods currently under investigation.
01 projects
Preprints
Research shared ahead of formal publication.
Preprint · 2026
Efficient Provably Private Classification with a Tabular Foundation Model
PrivTab embeds differential privacy within a tabular foundation model, enabling adaptation to sensitive datasets through in-context learning with provably private summaries.
02 projects
Published research
Peer reviewed work and published results.
Published · 2026
Privacy Leakage via Output Label Space and Differentially Private Continual Learning
Identifying a privacy side channel in continual learning and studying mechanisms that restore valid guarantees.
Published · 2025
Noise-Aware Differentially Private Variational Inference
Bayesian inference that accounts for privacy noise introduced during variational optimization.