I am a computer scientist, currently pursuing a doctorate degree from the Computer Science Department at Duke University. My academic advisors are Cynthia Rudin and Ron Parr. My research interests span across interpretable machine learning, responsible and trustworthy AI, AI in healthcare,
reinforcement learning, and reasoning.
Before joining Duke I worked for two years in Augmented Reality team at
Samsung Research and Development Institute Ukraine.
I received my M.S. and B.S. in Applied Mathematics from
the Taras Shevchenko National University of Kyiv, Department of Computer Science and Cybernetics.
I am currently on the academic job market. Please see here my research and diversity statements.
Publications
-
A Path to Simpler Models Starts with Noise
Neural Information Processing Systems (NeurIPS), 2023
Lesia Semenova, Harry Chen, Ronald Parr, and Cynthia Rudin
(bib) (video)
-
Sparse Density Trees and Lists: An Interpretable Alternative to High-Dimensional Histograms
INFORMS Journal on Data Science, 2023
Siong Thye Goh*, Lesia Semenova*, and Cynthia Rudin
(bib)
-
Impact of cannabis use on immune cell populations and the viral reservoir in people with HIV on suppressive antiretroviral therapy
The Journal of Infectious Disease (JID), 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
(bib)
- ProtoEEGNet: An interpretable approach for detecting interictal epileptiform discharges
Medical Imaging meets NeurIPS workshop, 2023 (oral).
Dennis Tang, Frank Willard, Ronan Tegerdine, Luke Triplett, Jon Donnelly, Luke Moffett, Lesia Semenova,
Alina Jade Barnett, Jin Jing, Cynthia Rudin, Brandon Westover
(bib)
(video)
- On the Existence of Simpler Machine Learning Models
ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT), 2022
Lesia Semenova, Cynthia Rudin, and Ronald Parr
(bib) (video)
- Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges
Statistics Surveys, 2022
Cynthia Rudin, Chaofan Chen, Zhi Chen, Haiyang Huang, Lesia Semenova, and Chudi Zhong
(bib)
-
Moving towards a more equal world, one ride at a time: studying public transportation initiatives using interpretable causal inference
Gaurav Rajesh Parikh, Jenny Huang, Albert Sun, Lesia Semenova, Cynthia Rudin
NeurIPS Workshop on Causality for Real-world Impact, 2022,
Won 2022 American Statistical Association Data Challenge Expo Student Competition
(bib)
- Multitask Learning for Citation Purpose Classification
Second Workshop on Scholarly Document Processing, NAACL, 2021
Alex Oesterling, Angikar Ghosal, Haoyang Yu, Rui Xin, Yasa Baig, Lesia Semenova, Cynthia Rudin
Won third place in the 3C Shared Task Competition. One of four oral presentations.
(bib)
Teaching
Please see here my
teaching statement and philosophy.
I served as a Teaching Assistant for the following classes:
- CS474, Data Science Competition, SP23, Duke University
- Terng Lecture Course on Interpretable Machine Learning, May 2022, Institute of Advanced Study
- CS474, Data Science Competition, SP22, Duke University
- CS474, Data Science Competition, SP21, Duke University
- CS571, Probabilistic Machine Learning, SP18, Duke University
- CS101, Introduction to Computer Science, SP17, Duke University