Zack Boner
Tagline:Ph.D. Student in Computer Science at Duke University, Advised by Dr. Cynthia Rudin. NSF Graduate Research Fellow.
Durham, NC, USA
About Me
I am a Ph.D. Candidate in Computer Science at Duke University, advised by Dr. Cynthia Rudin. I research interpretable machine learning with the objective of making AI more useful for real world domain experts. My research explains why simple models perform as well as black box models in a wide variety of tabular data domains. Towards this goal, I am investigating the simplifying effect of noise for several hypothesis spaces, especially sparse decision trees. I also study the underlying causes of the Rashomon Effect, where there are many approximately-equally-good models for real world data. Finally, I seek to understand the role of missing data in exacerbating the Rashomon Effect.
Recipient of the NSF Graduate Research Fellowship (GRFP).
Publications
Noise as a Natural Regularizer in Markov Decision Processes: Connecting Environmental Stochasticity and Policy Simplicity
Conference PaperPublisher:ICMLDate:2026Authors:Harry ChenMichal MoshkovitzYiyang SunLesia SemenovaZachery BonerCynthia RudinRonald ParrRashomon Sets of Falling Trees
Conference PaperPublisher:ICML (Spotlight)Date:2026Authors:Varun BabbarZachery BonerMargo SeltzerCynthia RudinDescription:Accepted to ICML 2026 in Seoul, SK as a Spotlight paper!
Shared first authorship between Babbar, V., Boner Z.
Leveraging Predictive Equivalence in Decision Trees
Conference PaperPublisher:ICMLDate:2025Authors:Hayden McTavishJon DonnellyZachery BonerMargo SeltzerCynthia RudinDescription:Accepted to ICML 2025 in Vancouver, BC.
Shared first authorship among Mctavish, H.; Donnelly, J.; Boner, Z.Transition Noise Facilitates Interpretability
Conference PaperPublisher:Workshop on Interpretable Policies in Reinforcement Learning@ RLC-2024Date:2024Authors:Ronald ParrCynthia RudinHarry ChenZachery BonerMichal MoshkovitzLesia SemenovaUsing Noise to Infer Aspects of Simplicity Without Learning
Conference PaperPublisher:The Thirty-eighth Annual Conference on Neural Information Processing SystemsDate:2024Authors:Zachery BonerHarry ChenLesia SemenovaRonald ParrCynthia RudinAmazing Things Come From Having Many Good Models
Conference PaperPublisher:ICMLDate:2024Authors:Cynthia RudinChudi ZhongLesia SemenovaMargo SeltzerRonald ParrJiachang LiuSrikar KattaJon DonnellyHarry ChenZachery BonerDeep Learning Risk Prediction of Bloodstream Infection in the Intensive Care Unit
Conference PaperPublisher:Knowledge Discovery and Data MiningDate:2022Authors:Zachery BonerChristopher C MooreN Rich Nguyen
Education
Bachelor of Science
from: 2019, until: 2023Field of study:Computer ScienceSchool:University of VirginiaLocation:Charlottesville, VA
Description2mj in Computer Science and Mathematics (BA; Concentration in Probability and Statistics)
Doctor of Philosophy
from: 2023, until: presentField of study:Computer ScienceSchool:Duke UniversityLocation:Durham, NC
DescriptionAdvised by Dr. Cynthia Rudin.
Research focus in Interpretable ML.