I aim to facilitate informed decision-making and empower machine learning practitioners, data scientists and policymakers with the tools needed to learn from data effectively, emphasizing interpretability, robustness, and trustworthiness. My goals are both to provide theoretical foundations that explain common phenomena observed in the data (especially for interpretable ML) and to design practical tools for reliable and trustworthy AI. The applications of my work are typically in high-stakes decision domains such as healthcare, finance, criminal justice, and governance.

In my recent research, I have established a theoretical foundation that explains when and why accurate interpretable/simple models exist. To do so, I leveraged the Rashomon effect, which is the phenomenon when multiple models perform equally well, and proposed the first effort in quantifying the Rashomon effect. Turns out that when the measure of the Rashomon effect is large, well-performing simpler models are more likely to exist.

Publications

Google Scholar | dblp | * denotes equal contribution
  1. 2024

    Zachery Boner*, Harry Chen*, Lesia Semenova*, Ronald Parr, Cynthia Rudin
    Advances in Neural Information Processing Systems (NeurIPS), 2024
    Cynthia Rudin, Chudi Zhong, Lesia Semenova, Margo Seltzer, Ronald Parr, Jiachang Liu, Srikar Katta, Jon Donnelly, Harry Chen, Zachery Boner
    Proceedings of the International Conference on Machine Learning (ICML), 2024
    spotlight
    Siong Thye Goh*, Lesia Semenova*, Cynthia Rudin
    INFORMS Journal on Data Science, 2024
    Ronald Parr, Cynthia Rudin, Harry Chen, Zachery Boner, Michal Moshkovitz, Lesia Semenova
    Workshop on Interpretable Policies in Reinforcement Learning@ RLC-2024, 2024
    oral
    Lesia Semenova, Yingfan Wang, Shane Falcinelli, Nancie Archin, Alicia D Cooper-Volkheimer, David M Margolis, Nilu Goonetilleke, David M Murdoch, Cynthia D Rudin, Edward P Browne
    eLife, 2024
  2. 2023

    Lesia Semenova, Harry Chen, Ronald Parr, Cynthia Rudin
    Advances in Neural Information Processing Systems (NeurIPS), 2023
    Dennis Tang, Frank Willard, Ronan Tegerdine, Luke Triplett, Jon Donnelly, Luke Moffett, Lesia Semenova, Alina Jade Barnett, Jin Jing, Cynthia Rudin, Brandon Westover
    Medical Imaging meets NeurIPS Workshop, 2023
    oral
    Chloe Qinyu Zhu, Muhang Tian, Lesia Semenova, Jiachang Liu, Jack Xu, Joseph Scarpa, Cynthia Rudin
    arXiv preprint arXiv:2311.13015, 2023
    Shane D Falcinelli, Alicia Volkheimer, Lesia Semenova, Ethan Wu, Alexander Richardson, Manickam Ashokkumar, David M Margolis, Nancie M Archin, Cynthia D Rudin, David Murdoch, Edward P Browne
    The Journal of Infectious Disease (JID), 2023
  3. 2022

    Lesia Semenova, Cynthia Rudin, Ronald Parr
    Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency (FAccT), 2022
    Gaurav Rajesh Parikh, Albert Sun, Jenny Huang, Lesia Semenova, Cynthia Rudin
    NeurIPS 2022 Workshop on Causality for Real-world Impact, 2022
    won 2022 American Statistical Association Data Challenge Expo Student Competition
    Cynthia Rudin, Chaofan Chen, Zhi Chen, Haiyang Huang, Lesia Semenova, Chudi Zhong
    Statistics Surveys, 2022
  4. 2021

    Alex Oesterling, Angikar Ghosal, Haoyang Yu, Rui Xin, Yasa Baig, Lesia Semenova, Cynthia Rudin
    Second Workshop on Scholarly Document Processing at NAACL, 2021
    oral, won third place in the 3C Shared Task Competition