Lucas Rosenblatt

PhD Candidate, Center for Responsible AI @NYU.

I am a second year PhD candidate at NYU where I am advised by Julia Stoyanovich and work closely with Christoper Musco and Bill Howe (of UW). I am affiliated with the NYU Center for Responsible AI. I am grateful to be supported by a NSF Graduate Research Fellowship.

Broadly, my work aims to answer open questions on data privacy, algorithmic fairness and AI safety, with an eye towards improving society and doing social good.

I was formerly a member of the Microsoft AI rotational program, working out of the New England Research and Development lab (and remotely during COVID!). In 2019 I graduated from Brown University, where I wrote a thesis about AI and self-data collection.

I happen to own a school bus that I’ve spent a lot of time converting into a mobile home and finding a permanent home for it in rural Vermont. If you like, I’ll give you some great reasons to buy a bus, and arguably some better reasons not to. I also make movies and write as much as I can.


Jul 7, 2023 Very happy to say that paper Epistemic Parity: Reproducibility as an Evaluation Metric for Differential Privacy was accepted into the Proceedings of VLDB 2023! This was a huge team effort, so a big thanks to everyone on the paper for over a year of hard work : )
Apr 13, 2023 I gave a talk at the excellent UCLA Synthetic Data Workshop. Thank you so much Guang Cheng for the invite and for organizing! Slides to be posted soon.
Mar 29, 2023 Very excited to have been awarded a 2023 NSF Graduate Research Fellowship!
Mar 7, 2023 Our paper The Possibility of Fairness: Revisiting the Impossibility Theorem in Practice was accepted into the Proceedings of FAccT 2023!
Feb 16, 2023 Our preprint The Possibility of Fairness: Revisiting the Impossibility Theorem in Practice is available on arXiv. Please take a look, we believe there are exciting implications for the algorithmic fairness community.
Nov 19, 2022 Our paper Counterfactual Fairness Is Basically Demographic Parity was accepted at AAAI 2023!
Oct 8, 2022 Our paper Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI was accepted at NLP for Positive Impact 2022, part of EMNLP 2022.
Jun 13, 2022 Our paper Spending Privacy Budget Wisely and Fairly was accepted at Theory and Practice of Differential Privacy 2022, part of ICML 2022.
Sep 25, 2021 I began my PhD at NYU! :smile:
Sep 1, 2021 Our paper PerfGuard: deploying ML-for-systems without performance regressions, almost! was published in PVLDB 2021.