Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Cynthia Rudin

Cynthia Rudin

Duke University

SegDiscover: Visual Concept Discovery via Unsupervised Semantic Segmentation


Apr 22, 2022
Haiyang Huang, Zhi Chen, Cynthia Rudin


  Access Paper or Ask Questions

Why Interpretable Causal Inference is Important for High-Stakes Decision Making for Critically Ill Patients and How To Do It


Mar 09, 2022
Harsh Parikh, Kentaro Hoffman, Haoqi Sun, Wendong Ge, Jin Jing, Rajesh Amerineni, Lin Liu, Jimeng Sun, Sahar Zafar, Aaron Struck, Alexander Volfovsky, Cynthia Rudin, M. Brandon Westover

Figure 1 for Why Interpretable Causal Inference is Important for High-Stakes Decision Making for Critically Ill Patients and How To Do It
Figure 2 for Why Interpretable Causal Inference is Important for High-Stakes Decision Making for Critically Ill Patients and How To Do It
Figure 3 for Why Interpretable Causal Inference is Important for High-Stakes Decision Making for Critically Ill Patients and How To Do It
Figure 4 for Why Interpretable Causal Inference is Important for High-Stakes Decision Making for Critically Ill Patients and How To Do It

  Access Paper or Ask Questions

Fast Sparse Classification for Generalized Linear and Additive Models


Feb 23, 2022
Jiachang Liu, Chudi Zhong, Margo Seltzer, Cynthia Rudin

Figure 1 for Fast Sparse Classification for Generalized Linear and Additive Models
Figure 2 for Fast Sparse Classification for Generalized Linear and Additive Models
Figure 3 for Fast Sparse Classification for Generalized Linear and Additive Models
Figure 4 for Fast Sparse Classification for Generalized Linear and Additive Models
* To Appear in AISTATS 2022 
  Access Paper or Ask Questions

Fast Sparse Decision Tree Optimization via Reference Ensembles


Dec 21, 2021
Hayden McTavish, Chudi Zhong, Reto Achermann, Ilias Karimalis, Jacques Chen, Cynthia Rudin, Margo Seltzer

Figure 1 for Fast Sparse Decision Tree Optimization via Reference Ensembles
Figure 2 for Fast Sparse Decision Tree Optimization via Reference Ensembles
Figure 3 for Fast Sparse Decision Tree Optimization via Reference Ensembles
Figure 4 for Fast Sparse Decision Tree Optimization via Reference Ensembles
* Accepted by AAAI 2022 
  Access Paper or Ask Questions

How Smart Guessing Strategies Can Yield Massive Scalability Improvements for Sparse Decision Tree Optimization


Dec 01, 2021
Hayden McTavish, Chudi Zhong, Reto Achermann, Ilias Karimalis, Jacques Chen, Cynthia Rudin, Margo Seltzer

Figure 1 for How Smart Guessing Strategies Can Yield Massive Scalability Improvements for Sparse Decision Tree Optimization
Figure 2 for How Smart Guessing Strategies Can Yield Massive Scalability Improvements for Sparse Decision Tree Optimization
Figure 3 for How Smart Guessing Strategies Can Yield Massive Scalability Improvements for Sparse Decision Tree Optimization
Figure 4 for How Smart Guessing Strategies Can Yield Massive Scalability Improvements for Sparse Decision Tree Optimization
* Accepted by AAAI 2022 
  Access Paper or Ask Questions

How to See Hidden Patterns in Metamaterials with Interpretable Machine Learning


Nov 10, 2021
Zhi Chen, Alexander Ogren, Chiara Daraio, L. Catherine Brinson, Cynthia Rudin

Figure 1 for How to See Hidden Patterns in Metamaterials with Interpretable Machine Learning
Figure 2 for How to See Hidden Patterns in Metamaterials with Interpretable Machine Learning
Figure 3 for How to See Hidden Patterns in Metamaterials with Interpretable Machine Learning
Figure 4 for How to See Hidden Patterns in Metamaterials with Interpretable Machine Learning
* Under review 
  Access Paper or Ask Questions

BacHMMachine: An Interpretable and Scalable Model for Algorithmic Harmonization for Four-part Baroque Chorales


Sep 15, 2021
Yunyao Zhu, Stephen Hahn, Simon Mak, Yue Jiang, Cynthia Rudin

Figure 1 for BacHMMachine: An Interpretable and Scalable Model for Algorithmic Harmonization for Four-part Baroque Chorales
Figure 2 for BacHMMachine: An Interpretable and Scalable Model for Algorithmic Harmonization for Four-part Baroque Chorales
Figure 3 for BacHMMachine: An Interpretable and Scalable Model for Algorithmic Harmonization for Four-part Baroque Chorales
Figure 4 for BacHMMachine: An Interpretable and Scalable Model for Algorithmic Harmonization for Four-part Baroque Chorales
* 7 pages, 7 figures 
  Access Paper or Ask Questions

Interpretable Mammographic Image Classification using Cased-Based Reasoning and Deep Learning


Jul 12, 2021
Alina Jade Barnett, Fides Regina Schwartz, Chaofan Tao, Chaofan Chen, Yinhao Ren, Joseph Y. Lo, Cynthia Rudin

Figure 1 for Interpretable Mammographic Image Classification using Cased-Based Reasoning and Deep Learning
Figure 2 for Interpretable Mammographic Image Classification using Cased-Based Reasoning and Deep Learning
Figure 3 for Interpretable Mammographic Image Classification using Cased-Based Reasoning and Deep Learning
Figure 4 for Interpretable Mammographic Image Classification using Cased-Based Reasoning and Deep Learning
* 10 pages, 6 figures, accepted for oral presentation at the IJCAI-21 Workshop on Deep Learning, Case-Based Reasoning, and AutoML: Present and Future Synergies. arXiv admin note: substantial text overlap with arXiv:2103.12308 
  Access Paper or Ask Questions

Multitask Learning for Citation Purpose Classification


Jun 24, 2021
Alex Oesterling, Angikar Ghosal, Haoyang Yu, Rui Xin, Yasa Baig, Lesia Semenova, Cynthia Rudin

Figure 1 for Multitask Learning for Citation Purpose Classification
Figure 2 for Multitask Learning for Citation Purpose Classification
Figure 3 for Multitask Learning for Citation Purpose Classification
* Second Workshop on Scholarly Document Processing 
  Access Paper or Ask Questions

A Holistic Approach to Interpretability in Financial Lending: Models, Visualizations, and Summary-Explanations


Jun 04, 2021
Chaofan Chen, Kangcheng Lin, Cynthia Rudin, Yaron Shaposhnik, Sijia Wang, Tong Wang

Figure 1 for A Holistic Approach to Interpretability in Financial Lending: Models, Visualizations, and Summary-Explanations
Figure 2 for A Holistic Approach to Interpretability in Financial Lending: Models, Visualizations, and Summary-Explanations
Figure 3 for A Holistic Approach to Interpretability in Financial Lending: Models, Visualizations, and Summary-Explanations
Figure 4 for A Holistic Approach to Interpretability in Financial Lending: Models, Visualizations, and Summary-Explanations

  Access Paper or Ask Questions

Playing Codenames with Language Graphs and Word Embeddings


May 12, 2021
Divya Koyyalagunta, Anna Sun, Rachel Lea Draelos, Cynthia Rudin

Figure 1 for Playing Codenames with Language Graphs and Word Embeddings
Figure 2 for Playing Codenames with Language Graphs and Word Embeddings
Figure 3 for Playing Codenames with Language Graphs and Word Embeddings
Figure 4 for Playing Codenames with Language Graphs and Word Embeddings
* Divya Koyyalagunta and Anna Sun contributed equally to this work. This is an arXiv version of the paper that has been accepted for publication in the Journal of Artificial Intelligence Research (JAIR) 
  Access Paper or Ask Questions

Ethical Implementation of Artificial Intelligence to Select Embryos in In Vitro Fertilization


Apr 30, 2021
Michael Anis Mihdi Afnan, Cynthia Rudin, Vincent Conitzer, Julian Savulescu, Abhishek Mishra, Yanhe Liu, Masoud Afnan

Figure 1 for Ethical Implementation of Artificial Intelligence to Select Embryos in In Vitro Fertilization
Figure 2 for Ethical Implementation of Artificial Intelligence to Select Embryos in In Vitro Fertilization
Figure 3 for Ethical Implementation of Artificial Intelligence to Select Embryos in In Vitro Fertilization
* AIES 2021 
  Access Paper or Ask Questions

IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography


Mar 23, 2021
Alina Jade Barnett, Fides Regina Schwartz, Chaofan Tao, Chaofan Chen, Yinhao Ren, Joseph Y. Lo, Cynthia Rudin

Figure 1 for IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography
Figure 2 for IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography
Figure 3 for IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography
Figure 4 for IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography
* 24 pages, 5 figures, 2 tables 
  Access Paper or Ask Questions

Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges


Mar 20, 2021
Cynthia Rudin, Chaofan Chen, Zhi Chen, Haiyang Huang, Lesia Semenova, Chudi Zhong

Figure 1 for Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges
Figure 2 for Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges
Figure 3 for Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges
Figure 4 for Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges

  Access Paper or Ask Questions

There Once Was a Really Bad Poet, It Was Automated but You Didn't Know It


Mar 05, 2021
Jianyou Wang, Xiaoxuan Zhang, Yuren Zhou, Christopher Suh, Cynthia Rudin

Figure 1 for There Once Was a Really Bad Poet, It Was Automated but You Didn't Know It
Figure 2 for There Once Was a Really Bad Poet, It Was Automated but You Didn't Know It
Figure 3 for There Once Was a Really Bad Poet, It Was Automated but You Didn't Know It
Figure 4 for There Once Was a Really Bad Poet, It Was Automated but You Didn't Know It
* Paper accepted and will be published at TACL (Transactions of the Association for Computational Linguistics) 2021 
  Access Paper or Ask Questions

dame-flame: A Python Library Providing Fast Interpretable Matching for Causal Inference


Jan 14, 2021
Neha R. Gupta, Vittorio Orlandi, Chia-Rui Chang, Tianyu Wang, Marco Morucci, Pritam Dey, Thomas J. Howell, Xian Sun, Angikar Ghosal, Sudeepa Roy, Cynthia Rudin, Alexander Volfovsky

Figure 1 for dame-flame: A Python Library Providing Fast Interpretable Matching for Causal Inference
Figure 2 for dame-flame: A Python Library Providing Fast Interpretable Matching for Causal Inference
* 5 pages, 1 figure; Reference and discussion of CEM corrected 
  Access Paper or Ask Questions

Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization


Dec 08, 2020
Yingfan Wang, Haiyang Huang, Cynthia Rudin, Yaron Shaposhnik

Figure 1 for Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization
Figure 2 for Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization
Figure 3 for Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization
Figure 4 for Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualization

  Access Paper or Ask Questions

Cryo-ZSSR: multiple-image super-resolution based on deep internal learning


Nov 22, 2020
Qinwen Huang, Ye Zhou, Xiaochen Du, Reed Chen, Jianyou Wang, Cynthia Rudin, Alberto Bartesaghi

Figure 1 for Cryo-ZSSR: multiple-image super-resolution based on deep internal learning
Figure 2 for Cryo-ZSSR: multiple-image super-resolution based on deep internal learning
Figure 3 for Cryo-ZSSR: multiple-image super-resolution based on deep internal learning
Figure 4 for Cryo-ZSSR: multiple-image super-resolution based on deep internal learning
* 11 pages, 4 figures 
  Access Paper or Ask Questions

Generalized and Scalable Optimal Sparse Decision Trees


Jul 17, 2020
Jimmy Lin, Chudi Zhong, Diane Hu, Cynthia Rudin, Margo Seltzer

Figure 1 for Generalized and Scalable Optimal Sparse Decision Trees
Figure 2 for Generalized and Scalable Optimal Sparse Decision Trees
Figure 3 for Generalized and Scalable Optimal Sparse Decision Trees
Figure 4 for Generalized and Scalable Optimal Sparse Decision Trees

  Access Paper or Ask Questions

Bandits for BMO Functions


Jul 17, 2020
Tianyu Wang, Cynthia Rudin

Figure 1 for Bandits for BMO Functions
Figure 2 for Bandits for BMO Functions
Figure 3 for Bandits for BMO Functions
Figure 4 for Bandits for BMO Functions

  Access Paper or Ask Questions

Generalized Optimal Sparse Decision Trees


Jun 15, 2020
Jimmy Lin, Chudi Zhong, Diane Hu, Cynthia Rudin, Margo Seltzer

Figure 1 for Generalized Optimal Sparse Decision Trees
Figure 2 for Generalized Optimal Sparse Decision Trees
Figure 3 for Generalized Optimal Sparse Decision Trees
Figure 4 for Generalized Optimal Sparse Decision Trees

  Access Paper or Ask Questions

In Pursuit of Interpretable, Fair and Accurate Machine Learning for Criminal Recidivism Prediction


May 08, 2020
Caroline Wang, Bin Han, Bhrij Patel, Feroze Mohideen, Cynthia Rudin

Figure 1 for In Pursuit of Interpretable, Fair and Accurate Machine Learning for Criminal Recidivism Prediction
Figure 2 for In Pursuit of Interpretable, Fair and Accurate Machine Learning for Criminal Recidivism Prediction
Figure 3 for In Pursuit of Interpretable, Fair and Accurate Machine Learning for Criminal Recidivism Prediction
Figure 4 for In Pursuit of Interpretable, Fair and Accurate Machine Learning for Criminal Recidivism Prediction

  Access Paper or Ask Questions

PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models


Mar 08, 2020
Sachit Menon, Alexandru Damian, Shijia Hu, Nikhil Ravi, Cynthia Rudin

Figure 1 for PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
Figure 2 for PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
Figure 3 for PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
Figure 4 for PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models
* Sachit Menon and Alexandru Damian contributed equally. CVPR 2020 camera-ready 
  Access Paper or Ask Questions

Adaptive Hyper-box Matching for Interpretable Individualized Treatment Effect Estimation


Mar 03, 2020
Marco Morucci, Vittorio Orlandi, Sudeepa Roy, Cynthia Rudin, Alexander Volfovsky

Figure 1 for Adaptive Hyper-box Matching for Interpretable Individualized Treatment Effect Estimation
Figure 2 for Adaptive Hyper-box Matching for Interpretable Individualized Treatment Effect Estimation
Figure 3 for Adaptive Hyper-box Matching for Interpretable Individualized Treatment Effect Estimation
Figure 4 for Adaptive Hyper-box Matching for Interpretable Individualized Treatment Effect Estimation

  Access Paper or Ask Questions

Almost-Matching-Exactly for Treatment Effect Estimation under Network Interference


Mar 02, 2020
M. Usaid Awan, Marco Morucci, Vittorio Orlandi, Sudeepa Roy, Cynthia Rudin, Alexander Volfovsky

Figure 1 for Almost-Matching-Exactly for Treatment Effect Estimation under Network Interference
Figure 2 for Almost-Matching-Exactly for Treatment Effect Estimation under Network Interference
Figure 3 for Almost-Matching-Exactly for Treatment Effect Estimation under Network Interference
Figure 4 for Almost-Matching-Exactly for Treatment Effect Estimation under Network Interference

  Access Paper or Ask Questions

Concept Whitening for Interpretable Image Recognition


Feb 05, 2020
Zhi Chen, Yijie Bei, Cynthia Rudin

Figure 1 for Concept Whitening for Interpretable Image Recognition
Figure 2 for Concept Whitening for Interpretable Image Recognition
Figure 3 for Concept Whitening for Interpretable Image Recognition
Figure 4 for Concept Whitening for Interpretable Image Recognition

  Access Paper or Ask Questions

A study in Rashomon curves and volumes: A new perspective on generalization and model simplicity in machine learning


Aug 05, 2019
Lesia Semenova, Cynthia Rudin

Figure 1 for A study in Rashomon curves and volumes: A new perspective on generalization and model simplicity in machine learning
Figure 2 for A study in Rashomon curves and volumes: A new perspective on generalization and model simplicity in machine learning
Figure 3 for A study in Rashomon curves and volumes: A new perspective on generalization and model simplicity in machine learning
Figure 4 for A study in Rashomon curves and volumes: A new perspective on generalization and model simplicity in machine learning

  Access Paper or Ask Questions

Interpretable Almost-Matching-Exactly With Instrumental Variables


Jul 28, 2019
M. Usaid Awan, Yameng Liu, Marco Morucci, Sudeepa Roy, Cynthia Rudin, Alexander Volfovsky

Figure 1 for Interpretable Almost-Matching-Exactly With Instrumental Variables
Figure 2 for Interpretable Almost-Matching-Exactly With Instrumental Variables
Figure 3 for Interpretable Almost-Matching-Exactly With Instrumental Variables
Figure 4 for Interpretable Almost-Matching-Exactly With Instrumental Variables
* Proceedings of the Thirty-fifth Conference on Uncertainty in Artificial Intelligence (UAI 2019) 
  Access Paper or Ask Questions

Reducing Exploration of Dying Arms in Mortal Bandits


Jul 04, 2019
Stefano Tracà, Cynthia Rudin, Weiyu Yan

Figure 1 for Reducing Exploration of Dying Arms in Mortal Bandits
Figure 2 for Reducing Exploration of Dying Arms in Mortal Bandits
Figure 3 for Reducing Exploration of Dying Arms in Mortal Bandits
* Conference: UAI 2019 
  Access Paper or Ask Questions