Publications

Here is work that I've either submitted somewhere, or that's up on arXiv.

2024

  1. A Simple and Practical Method for Reducing the Disparate Impact of Differential Privacy
    Lucas Rosenblatt, Julia Stoyanovich, and Christopher Musco
    Proceedings of AAAI 2024
  2. I Open at the Close: A Deep Reinforcement Learning Evaluation of Open Streets Initiatives
    R. Teal Witter, and Lucas Rosenblatt
    Proceedings of AAAI 2024

2023

  1. Counterfactual Fairness Is Basically Demographic Parity
    Lucas Rosenblatt, and R Teal Witter
    Proceedings of AAAI 2023
  2. Epistemic Parity: Reproducibility as an Evaluation Metric for Differential Privacy
    Lucas Rosenblatt, Anastasia Holovenko, Taras Rumezhak, Andrii Stadnik, Bernease Herman, Julia Stoyanovich, and Bill Howe
    Proceedings of the VLDB Endowment 2023
  3. The Possibility of Fairness: Revisiting the Impossibility Theorem in Practice
    Andrew Bell, Lucius Bynum, Nazarii Drushchak, Tetiana Herasymova, Lucas Rosenblatt, and Julia Stoyanovich
    Proceedings of the Conference on Fairness, Accountability, and Transparency (ACM FAccT) 2023
  4. Top-down Green-ups: Satellite Sensing and Deep Models to Predict Buffelgrass Phenology
    Lucas Rosenblatt, Bin Han, Erin Posthumus, Theresa Crimmins, and Bill Howe
    Tackling Climate Change with Machine Learning @ NeurIPS 2023

2022

  1. Spending Privacy Budget Fairly and Wisely
    Lucas Rosenblatt, Joshua Allen, and Julia Stoyanovich
    Theory and Practice of Differential Privacy 2022 (@ICML) 2022
  2. 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

2021

  1. 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
    Proceedings of the VLDB Endowment 2021

2020

  1. Differentially private synthetic data: Applied evaluations and enhancements
    Lucas Rosenblatt, Xiaoyan Liu, Samira Pouyanfar, Eduardo Leon, Anuj Desai, and Joshua Allen
    arXiv preprint arXiv:2011.05537 2020
  2. PerfGuard: Deploying ML-for-Systems without Performance Regressions
    HM Sajjad Hossain, Lucas Rosenblatt, Gilbert Antonius, Irene Shaffer, Remmelt Ammerlaan, Abhishek Roy, Markus Weimer, Hiren Patel, Marc Friedman, Shi Qiao, Peter Orenberg, and  others
    MLOps 2020

2018

  1. 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

2017

  1. Vocalide: An ide for programming via speech recognition
    Lucas Rosenblatt
    In Proceedings of the 19th International ACM SIGACCESS Conference on Computers and Accessibility 2017