Lydia Zakynthinou
where else to find them
linkedin:lydia-zakynthinou-a9408a94
what they talk about
where they keep going back
no series more than once — all 4 in the filters
on a stage with
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Dimension-free Private Mean Estimation for Anisotropic Distributions | Trust in Decentralized Systems 2026 | 2026-03-16 |
Provides an (ε,δ)-DP estimator that achieves Euclidean error ≤α with sample complexity n ≳ tr(Σ)/α^2 + tr(Σ^{1/2})/(αε), and proves that bound is optimal up to… | ||
| Tutorial: Privacy, Part I | Federated and Collaborative Learning Boot Camp 2026 | 2026-01-26 |
Covers rigorous limits and concrete attacks: models repeatedly emit training data (GPT-2 and diffusion memorization, census reconstructions), a classic result… | ||
| Tutorial: Privacy, Part II | Federated and Collaborative Learning Boot Camp 2026 | 2026-01-26 |
Defines differential privacy as an output-distribution bound parametrized by epsilon/delta, proves noise calibrated to global sensitivity (e.g., mean of… | ||
| Tutorial: Privacy, Part III | Federated and Collaborative Learning Boot Camp 2026 | 2026-01-26 |
DP-SGD suffers from realistic sampling gaps and amplification limits, so the lecture reframes iterative training as continual observation and private release… | ||
| Data privacy and reliable learning | Meet the Fellows Welcome Event Fall 2024 | 2024-09-03 |
Shows that private learners can achieve dimension-free error for some mean estimation tasks by using instance-adaptive bounds and exploiting low effective… | ||
| From Robustness to Privacy and Back | 9th Annual Simons Institute Industry Day | 2023-11-02 |
Gives a black-box transformation that turns any robust estimator into an ε‑differentially private estimator, with the DP error matching the robust error for a… | ||
| nothing matches | ||