Lucas is a third year PhD candidate at NYU advised by Julia Stoyanovich and working closely with Christoper Musco and Bill Howe (of UW). He is supported by a NSF Graduate Research Fellowship. His work aims to answer open questions on data privacy, algorithmic fairness and AI safety, with an eye towards improving society and doing social good.
He was formerly a member of the Microsoft AI rotational program, working out of the New England Research and Development lab (and remotely during COVID!). He graduated from Brown University in 2019.
Selected publications
Epistemic Parity: Reproducibility as an Evaluation Metric for Differential Privacy
Lucas Rosenblatt, Bernease Herman, Anastasia Holovenko, Wonkwon Lee, Joshua R. Loftus, Elizabeth McKinnie, Taras Rumezhak, Andrii Stadnik, Bill Howe, and Julia Stoyanovich
@article{DBLP:journals/sigmod/RosenblattHHLLMRSHS24,author={Rosenblatt, Lucas and Herman, Bernease and Holovenko, Anastasia and Lee, Wonkwon and Loftus, Joshua R. and McKinnie, Elizabeth and Rumezhak, Taras and Stadnik, Andrii and Howe, Bill and Stoyanovich, Julia},title={Epistemic Parity: Reproducibility as an Evaluation Metric for Differential
Privacy},journal={{SIGMOD} Rec.},volume={53},number={1},pages={65--74},year={2024},url={https://doi.org/10.1145/3665252.3665267},doi={10.1145/3665252.3665267},keywords={journal,privacy,RAIforUkraine},author+an={1=self;3=self;4=self;6=self;7=self;8=self;10=self}}
The Possibility of Fairness: Revisiting the Impossibility Theorem in Practice
Andrew Bell, Lucius Bynum, Nazarii Drushchak, Tetiana Zakharchenko, Lucas Rosenblatt, and Julia Stoyanovich
In Proceedings of the ACM Conference on Fairness, Accountability, and Transparency, FAccT, Chicago, IL, USA 2023
@inproceedings{DBLP:conf/fat/BellBDZRS23,author={Bell, Andrew and Bynum, Lucius and Drushchak, Nazarii and Zakharchenko, Tetiana and Rosenblatt, Lucas and Stoyanovich, Julia},title={The Possibility of Fairness: Revisiting the Impossibility Theorem
in Practice},booktitle={Proceedings of the {ACM} Conference on Fairness, Accountability,
and Transparency, FAccT, Chicago, IL, USA},pages={400--422},publisher={{ACM}},year={2023},doi={10.1145/3593013.3594007},keywords={conference,fair,RAIforUkraine},author+an={1=self;2=self;3=self;4=self;5=self;6=self}}
Counterfactual Fairness Is Basically Demographic Parity
Lucas Rosenblatt, and R Teal Witter
Proceedings of the AAAI Conference on Artificial Intelligence 2023
@article{rosenblatt2022counterfactual,title={Counterfactual Fairness Is Basically Demographic Parity},author={Rosenblatt, Lucas and Witter, R Teal},journal={Proceedings of the AAAI Conference on Artificial Intelligence},year={2023},keywords={fairness, counterfactuals, causal},}
Spending Privacy Budget Fairly and Wisely
Lucas Rosenblatt, Joshua Allen, and Julia Stoyanovich
Theory and Practice of Differential Privacy (@ICML) 2022
@article{rosenblatt2022spending,title={Spending Privacy Budget Fairly and Wisely},author={Rosenblatt, Lucas and Allen, Joshua and Stoyanovich, Julia},journal={Theory and Practice of Differential Privacy (@ICML)},year={2022},keywords={differential privacy, fairness, databases},}
Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI
Lucas Rosenblatt, Lorena Piedras, and Julia Wilkins
In Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI) 2022
@inproceedings{rosenblatt2022critical,title={Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI},author={Rosenblatt, Lucas and Piedras, Lorena and Wilkins, Julia},booktitle={Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI)},pages={15--24},year={2022},keywords={fairness, nlp, benchmark},}
Differentially private synthetic data: Applied evaluations and enhancements
Lucas Rosenblatt, Xiaoyan Liu, Samira Pouyanfar, Eduardo Leon, Anuj Desai, and Joshua Allen
@article{rosenblatt2020differentially,title={Differentially private synthetic data: Applied evaluations and enhancements},author={Rosenblatt, Lucas and Liu, Xiaoyan and Pouyanfar, Samira and de Leon, Eduardo and Desai, Anuj and Allen, Joshua},journal={arXiv preprint arXiv:2011.05537},year={2020},keywords={differential privacy, benchmark},}
PerfGuard: deploying ML-for-systems without performance regressions, almost!
Remmelt Ammerlaan, Gilbert Antonius, Marc Friedman, HM Sajjad Hossain, Alekh Jindal, Peter Orenberg, Hiren Patel, Shi Qiao, Vijay Ramani, Lucas Rosenblatt, and others
@article{ammerlaan2021perfguard,title={PerfGuard: deploying ML-for-systems without performance regressions, almost!},author={Ammerlaan, Remmelt and Antonius, Gilbert and Friedman, Marc and Hossain, HM Sajjad and Jindal, Alekh and Orenberg, Peter and Patel, Hiren and Qiao, Shi and Ramani, Vijay and Rosenblatt, Lucas and others},journal={Proceedings of the VLDB Endowment},volume={14},number={13},pages={3362--3375},year={2021},publisher={VLDB Endowment},keywords={ml, systems, performance, data},}
Vocal programming for people with upper-body motor impairments
Lucas Rosenblatt, Patrick Carrington, Kotaro Hara, and Jeffrey P Bigham
In Proceedings of the 15th International Web for All Conference 2018
@inproceedings{rosenblatt2018vocal,title={Vocal programming for people with upper-body motor impairments},author={Rosenblatt, Lucas and Carrington, Patrick and Hara, Kotaro and Bigham, Jeffrey P},booktitle={Proceedings of the 15th International Web for All Conference},pages={1--10},year={2018},keywords={accessibility, vocal, programming},}
All Aboard! Making AI Education Accessible
Falaah Arif Khan, Lucius Bynum, Amy Hurst, Lucas Rosenblatt, Meghana Shanbhogue, Mona Sloane, and Julia Stoyanovich
Center for Responsible AI, New York University 2023
@article{AllAboard,author={{Arif Khan}, Falaah and Bynum, Lucius and Hurst, Amy and Rosenblatt, Lucas and Shanbhogue, Meghana and Sloane, Mona and Stoyanovich, Julia},title={{All Aboard! Making AI Education Accessible}},journal={Center for Responsible AI, New York University},keywords={panel,education,weareai},year={2023},}
Spending Privacy Budget Fairly and Wisely
Lucas Rosenblatt, Joshua Allen, and Julia Stoyanovich
@article{DBLP:journals/corr/abs-2204-12903,author={Rosenblatt, Lucas and Allen, Joshua and Stoyanovich, Julia},title={Spending Privacy Budget Fairly and Wisely},journal={CoRR},volume={abs/2204.12903},year={2022},doi={10.48550/arXiv.2204.12903},eprinttype={arXiv},eprint={2204.12903},timestamp={Fri, 29 Apr 2022 13:26:05 +0200},bibsource={dblp computer science bibliography, https://dblp.org},keywords={working,privacy,fairness},author+an={1=self;3=self}}
Epistemic Parity: Reproducibility as an Evaluation Metric for Differential Privacy
Lucas Rosenblatt, Bernease Herman, Anastasia Holovenko, Wonkwon Lee, Joshua R. Loftus, Elizabeth Mckinnie, Taras Rumezhak, Andrii Stadnik, Bill Howe, and Julia Stoyanovich
@article{DBLP:journals/pvldb/RosenblattHHLLM23,author={Rosenblatt, Lucas and Herman, Bernease and Holovenko, Anastasia and Lee, Wonkwon and Loftus, Joshua R. and Mckinnie, Elizabeth and Rumezhak, Taras and Stadnik, Andrii and Howe, Bill and Stoyanovich, Julia},title={Epistemic Parity: Reproducibility as an Evaluation Metric for Differential
Privacy},journal={Proc. {VLDB} Endow.},volume={16},number={11},pages={3178--3191},year={2023},doi={10.14778/3611479.3611517},timestamp={Mon, 23 Oct 2023 16:16:16 +0200},biburl={https://dblp.org/rec/journals/pvldb/RosenblattHHLLM23.bib},keywords={journal,privacy,RAIforUkraine},author+an={1=self;3=self;4=self;6=self;7=self;8=self;10=self}}
A Simple and Practical Method for Reducing the Disparate Impact of Differential Privacy
Lucas Rosenblatt, Julia Stoyanovich, and Christopher Musco
In Thirty-Eighth AAAI Conference on Artificial Intelligence, AAAI 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, IAAI 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2014, February 20-27, 2024, Vancouver, Canada 2024
@inproceedings{DBLP:conf/aaai/RosenblattSM24,author={Rosenblatt, Lucas and Stoyanovich, Julia and Musco, Christopher},editor={Wooldridge, Michael J. and Dy, Jennifer G. and Natarajan, Sriraam},title={A Simple and Practical Method for Reducing the Disparate Impact of
Differential Privacy},booktitle={Thirty-Eighth {AAAI} Conference on Artificial Intelligence, {AAAI}
2024, Thirty-Sixth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2024, Fourteenth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2014, February 20-27, 2024, Vancouver,
Canada},pages={21554--21562},publisher={{AAAI} Press},year={2024},url={https://doi.org/10.1609/aaai.v38i19.30153},doi={10.1609/AAAI.V38I19.30153},keywords={fairness,privacy,conference},author+an={1=self;2=self}}