Research

My research focuses on developing interpretable machine learning algorithms and pipelines to help people make better decisions in high-stakes situations.

I work on optimizing interpretable models such as decision trees and generalized additive models with ℓ0-based sparsity constraints. These algorithms are able to find simple, interpretable models that achieve accuracy comparable to black-box models.

My recent research focuses on the Rashomon set, which enumerates, stores, and visualizes all models within ε of the optimal loss. This paradigm enables seamless user interaction. Models that satisfy arbitrary user constraints (e.g. monotonicity, fairness) can be found by simply filtering over the Rashomon set instead of retraining. Model-free analysis can be conducted on metrics such as variable importance.


Areas: Machine Learning, Optimization, Human-Model Interaction

Topics: Interpretability, Rashomon Sets, Logical Models

Applications: Healthcare, Finance, Criminal Justice

Publications

(* indicates co-first authors, equal contribution)

The Amazing Things that Come From Having Many Good Models

Cynthia Rudin, Chudi Zhong, Lesia Semenova, Margo Seltzer, Ronald Parr, Jiachang Liu, Srikar Katta, Jon Donnelly, Harry Chen, Zachery Boner

ICML 2024 (Spotlight)

Spotlight Paper at ICML 2024

Exploring and Interacting with the Set of Good Sparse Generalized Additive Models

Chudi Zhong*, Zhi Chen*, Jiachang Liu, Margo Seltzer, Cynthia Rudin

NeurIPS 2023

Paper Code Video

OKRidge: Scalable Optimal k-Sparse Ridge Regression for Learning Dynamical Systems

Jiachang Liu, Sam Rosen, Chudi Zhong, Cynthia Rudin

NeurIPS 2023 (Spotlight)

Spotlight Paper at NeurIPS 2023

Paper

Exploring the Whole Rashomon Set of Sparse Decision Trees

Rui Xin*, Chudi Zhong*, Zhi Chen*, Takuya Takagi, Margo Seltzer, Cynthia Rudin

NeurIPS 2022 (Oral)

Oral Paper at NeurIPS 2022

Finalist, Data Mining Best Student Paper Award, INFORMS, 2022

Paper Code

FasterRisk: Fast and Accurate Interpretable Risk Scores

Jiachang Liu*, Chudi Zhong*, Boxuan Li, Margo Seltzer, Cynthia Rudin

NeurIPS 2022

Paper Code

TimberTrek: Exploring and Curating Trustworthy Decision Trees with Interactive Visualization

Zijie Wang, Chudi Zhong, Rui Xin, Takuya Takagi, Zhi Chen, Duen Horng Chau, Cynthia Rudin, Margo Seltzer

IEEE VIS 2022

Paper Code Demo

Fast Sparse Classification for Generalized Linear and Additive Models

Jiachang Liu, Chudi Zhong, Margo Seltzer, Cynthia Rudin

AISTATS 2022

Paper Code

Fast Sparse Decision Tree Optimization via Reference Ensembles

Hayden McTavish*, Chudi Zhong*, Reto Achermann, Ilias Karimalis, Jacques Chen, Cynthia Rudin, Margo Seltzer

AAAI 2022

Paper Code

Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges

Cynthia Rudin, Chaofan Chen, Zhi Chen, Haiyang Huang, Lesia Semenova, Chudi Zhong

Statistics Surveys 2022

Paper

Generalized and Scalable Optimal Sparse Decision Trees

Jimmy Lin*, Chudi Zhong*, Diane Hu, Cynthia Rudin, Margo Seltzer

ICML 2020

Paper Code