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 Finale Doshi-Velez

Learning Under Adversarial and Interventional Shifts


Mar 29, 2021
Harvineet Singh, Shalmali Joshi, Finale Doshi-Velez, Himabindu Lakkaraju

* 19 pages including 5 pages appendix, 6 figures, 2 tables. Preliminary version presented at Causal Discovery & Causality-Inspired Machine Learning Workshop 2020 

  Access Paper or Ask Questions

Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement


Feb 09, 2021
Andrew Slavin Ross, Finale Doshi-Velez


  Access Paper or Ask Questions

Evaluating the Interpretability of Generative Models by Interactive Reconstruction


Feb 02, 2021
Andrew Slavin Ross, Nina Chen, Elisa Zhao Hang, Elena L. Glassman, Finale Doshi-Velez

* CHI 2021 accepted paper 

  Access Paper or Ask Questions

Preferential Mixture-of-Experts: Interpretable Models that Rely on Human Expertise as much as Possible


Jan 13, 2021
Melanie F. Pradier, Javier Zazo, Sonali Parbhoo, Roy H. Perlis, Maurizio Zazzi, Finale Doshi-Velez

* 10 pages, 5 figures, 4 tables, AMIA 2021 Virtual Informatics Summit 

  Access Paper or Ask Questions

Identifying Decision Points for Safe and Interpretable Reinforcement Learning in Hypotension Treatment


Jan 09, 2021
Kristine Zhang, Yuanheng Wang, Jianzhun Du, Brian Chu, Leo Anthony Celi, Ryan Kindle, Finale Doshi-Velez

* NeurIPS 2020 Machine Learning for Health (ML4H) Workshop 

  Access Paper or Ask Questions

Artificial Intelligence & Cooperation


Dec 10, 2020
Elisa Bertino, Finale Doshi-Velez, Maria Gini, Daniel Lopresti, David Parkes

* A Computing Community Consortium (CCC) white paper, 4 pages 

  Access Paper or Ask Questions

Learning Interpretable Concept-Based Models with Human Feedback


Dec 04, 2020
Isaac Lage, Finale Doshi-Velez


  Access Paper or Ask Questions

Incorporating Interpretable Output Constraints in Bayesian Neural Networks


Oct 21, 2020
Wanqian Yang, Lars Lorch, Moritz A. Graule, Himabindu Lakkaraju, Finale Doshi-Velez

* 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada. Code available at: https://github.com/dtak/ocbnn-public 

  Access Paper or Ask Questions

Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks


Jul 14, 2020
Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez

* Accepted at the International Conference on Machine Learning (ICML) Workshop on Uncertainty and Robustness in Deep Learning (UDL) 2020 

  Access Paper or Ask Questions

BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty


Jul 12, 2020
Théo Guénais, Dimitris Vamvourellis, Yaniv Yacoby, Finale Doshi-Velez, Weiwei Pan

* ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning 

  Access Paper or Ask Questions

Learned Uncertainty-Aware (LUNA) Bases for Bayesian Regression using Multi-Headed Auxiliary Networks


Jul 08, 2020
Sujay Thakur, Cooper Lorsung, Yaniv Yacoby, Finale Doshi-Velez, Weiwei Pan

* ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning 

  Access Paper or Ask Questions

Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs


Jun 29, 2020
Jianzhun Du, Joseph Futoma, Finale Doshi-Velez

* 20 pages, 7 figures 

  Access Paper or Ask Questions

PAC Bounds for Imitation and Model-based Batch Learning of Contextual Markov Decision Processes


Jun 11, 2020
Yash Nair, Finale Doshi-Velez


  Access Paper or Ask Questions

Is Deep Reinforcement Learning Ready for Practical Applications in Healthcare? A Sensitivity Analysis of Duel-DDQN for Sepsis Treatment


May 08, 2020
MingYu Lu, Zachary Shahn, Daby Sow, Finale Doshi-Velez, Li-wei H. Lehman

* 10 pages, 9 figures 

  Access Paper or Ask Questions

Power-Constrained Bandits


Apr 13, 2020
Jiayu Yao, Emma Brunskill, Weiwei Pan, Susan Murphy, Finale Doshi-Velez


  Access Paper or Ask Questions

Characterizing and Avoiding Problematic Global Optima of Variational Autoencoders


Mar 17, 2020
Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez

* PMLR 118:1-17, 2020 
* Accepted at the Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference 2019 

  Access Paper or Ask Questions

Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions


Feb 14, 2020
Omer Gottesman, Joseph Futoma, Yao Liu, Sonali Parbhoo, Leo Anthony Celi, Emma Brunskill, Finale Doshi-Velez

* Change: Correction of typo in meta-data author names 

  Access Paper or Ask Questions

POPCORN: Partially Observed Prediction COnstrained ReiNforcement Learning


Jan 13, 2020
Joseph Futoma, Michael C. Hughes, Finale Doshi-Velez

* Accepted, to appear at AISTATS 2020, Palermo. Note that this version is not the final camera-ready; that will appear in a few weeks 

  Access Paper or Ask Questions

Identifying Distinct, Effective Treatments for Acute Hypotension with SODA-RL: Safely Optimized Diverse Accurate Reinforcement Learning


Jan 09, 2020
Joseph Futoma, Muhammad A. Masood, Finale Doshi-Velez

* Accepted for publication at the AMIA 2020 Informatics Summit. This version contains an updated appendix with additional figures not found in the page-constrained AMIA version, so treat this version as the most up-to-date 

  Access Paper or Ask Questions

Towards Expressive Priors for Bayesian Neural Networks: Poisson Process Radial Basis Function Networks


Dec 12, 2019
Beau Coker, Melanie F. Pradier, Finale Doshi-Velez


  Access Paper or Ask Questions

Ensembles of Locally Independent Prediction Models


Nov 27, 2019
Andrew Slavin Ross, Weiwei Pan, Leo Anthony Celi, Finale Doshi-Velez

* This is an expansion of arXiv:1806.08716 with different applications and focus, accepted to AAAI 2020 

  Access Paper or Ask Questions

Prediction Focused Topic Models for Electronic Health Records


Nov 15, 2019
Jason Ren, Russell Kunes, Finale Doshi-Velez

* Machine Learning for Health (ML4H) at NeurIPS 2019 - Extended Abstract. arXiv admin note: substantial text overlap with arXiv:1910.05495 

  Access Paper or Ask Questions

Learning Deep Bayesian Latent Variable Regression Models that Generalize: When Non-identifiability is a Problem


Nov 01, 2019
Yaniv Yacoby, Weiwei Pan, Finale Doshi-Velez

* Accepted at ICML's Uncertainty and Robustness in Deep Learning Workshop 2019 

  Access Paper or Ask Questions

Prediction Focused Topic Models via Vocab Selection


Oct 12, 2019
Jason Ren, Russell Kunes, Finale Doshi-Velez

* Extended Abstract to appear in ML4Health and HCML Neurips Workshops, 8 pages 

  Access Paper or Ask Questions

Optimizing for Interpretability in Deep Neural Networks with Tree Regularization


Aug 14, 2019
Mike Wu, Sonali Parbhoo, Michael C. Hughes, Volker Roth, Finale Doshi-Velez

* arXiv admin note: substantial text overlap with arXiv:1908.04494, arXiv:1711.06178 

  Access Paper or Ask Questions

Regional Tree Regularization for Interpretability in Black Box Models


Aug 13, 2019
Mike Wu, Sonali Parbhoo, Michael Hughes, Ryan Kindle, Leo Celi, Maurizio Zazzi, Volker Roth, Finale Doshi-Velez


  Access Paper or Ask Questions

Quality of Uncertainty Quantification for Bayesian Neural Network Inference


Jun 24, 2019
Jiayu Yao, Weiwei Pan, Soumya Ghosh, Finale Doshi-Velez

* Accepted to ICML UDL 2019 

  Access Paper or Ask Questions