Finale Doshi-Velez

Considerations for Evaluation and Generalization in Interpretable Machine Learning

Been Kim, Finale Doshi-Velez, Finale Doshi-Velez, 2018 .

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

Yao Liu, Emma Brunskill, Joseph Futoma, 2020, ICML.

Human Evaluation of Models Built for Interpretability

Samuel J. Gershman, Emily Chen, Been Kim, 2019, HCOMP.

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

Joseph Futoma, Finale Doshi-Velez, Muhammad A. Masood, 2020, AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science.

Artificial Intelligence & Cooperation pdf

Elisa Bertino, Maria Gini, Daniel Lopresti, 2020, ArXiv.

Prediction Focused Topic Models via Feature Selection

Finale Doshi-Velez, Jason Ren, Russell Kunes, 2020, AISTATS.

Prediction Focused Topic Models for Electronic Health Records pdf

Finale Doshi-Velez, Jason Ren, Russell Kunes, 2019, ArXiv.

Summarizing agent strategies

David Sarne, Ofra Amir, Finale Doshi-Velez, 2019, Autonomous Agents and Multi-Agent Systems.

Bayesian Nonparametric Methods for Partially-Observable Reinforcement Learning

David Pfau, Nicholas Roy, Frank Wood, 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Towards A Rigorous Science of Interpretable Machine Learning

Been Kim, Finale Doshi-Velez, Finale Doshi-Velez, 2017, 1702.08608.

Improving counterfactual reasoning with kernelised dynamic mixing models

Andrew Slavin Ross, Volker Roth, Finale Doshi-Velez, 2018, PloS one.