Timezone: »
Domains where supervised models are deployed often come with task-specific constraints, such as prior expert knowledge on the ground-truth function, or desiderata like safety and fairness. We introduce a novel probabilistic framework for reasoning with such constraints and formulate a prior that enables us to effectively incorporate them into Bayesian neural networks (BNNs), including a variant that can be amortized over tasks. The resulting Output-Constrained BNN (OC-BNN) is fully consistent with the Bayesian framework for uncertainty quantification and is amenable to black-box inference. Unlike typical BNN inference in uninterpretable parameter space, OC-BNNs widen the range of functional knowledge that can be incorporated, especially for model users without expertise in machine learning. We demonstrate the efficacy of OC-BNNs on real-world datasets, spanning multiple domains such as healthcare, criminal justice, and credit scoring.
Author Information
Wanqian Yang (Harvard University)
Lars Lorch (Harvard)
Moritz Graule (Harvard University)
Himabindu Lakkaraju (Harvard)
Hima Lakkaraju is an Assistant Professor at Harvard University focusing on explainability, fairness, and robustness of machine learning models. She has also been working with various domain experts in criminal justice and healthcare to understand the real world implications of explainable and fair ML. Hima has recently been named one of the 35 innovators under 35 by MIT Tech Review, and has received best paper awards at SIAM International Conference on Data Mining (SDM) and INFORMS. She has given invited workshop talks at ICML, NeurIPS, AAAI, and CVPR, and her research has also been covered by various popular media outlets including the New York Times, MIT Tech Review, TIME, and Forbes. For more information, please visit: https://himalakkaraju.github.io/
Finale Doshi-Velez (Harvard)
Related Events (a corresponding poster, oral, or spotlight)
-
2020 Spotlight: Incorporating Interpretable Output Constraints in Bayesian Neural Networks »
Fri Dec 11th 03:50 -- 04:00 AM Room Orals & Spotlights: Neuroscience/Probabilistic
More from the Same Authors
-
2020 Workshop: I Can’t Believe It’s Not Better! Bridging the gap between theory and empiricism in probabilistic machine learning »
Jessica Forde · Francisco Ruiz · Melanie Fernandez Pradier · Aaron Schein · Finale Doshi-Velez · Isabel Valera · David Blei · Hanna Wallach -
2020 Tutorial: (Track2) Explaining Machine Learning Predictions: State-of-the-art, Challenges, and Opportunities Q&A »
Himabindu Lakkaraju · Julius Adebayo · Sameer Singh -
2020 Poster: Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses »
Kaivalya Rawal · Himabindu Lakkaraju -
2020 Poster: Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs »
Jianzhun Du · Joseph Futoma · Finale Doshi-Velez -
2020 Tutorial: (Track2) Explaining Machine Learning Predictions: State-of-the-art, Challenges, and Opportunities »
Himabindu Lakkaraju · Julius Adebayo · Sameer Singh -
2018 Poster: Human-in-the-Loop Interpretability Prior »
Isaac Lage · Andrew Ross · Samuel J Gershman · Been Kim · Finale Doshi-Velez -
2018 Spotlight: Human-in-the-Loop Interpretability Prior »
Isaac Lage · Andrew Ross · Samuel J Gershman · Been Kim · Finale Doshi-Velez -
2018 Poster: Representation Balancing MDPs for Off-policy Policy Evaluation »
Yao Liu · Omer Gottesman · Aniruddh Raghu · Matthieu Komorowski · Aldo Faisal · Finale Doshi-Velez · Emma Brunskill -
2017 Poster: Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes »
Taylor Killian · Samuel Daulton · Finale Doshi-Velez · George Konidaris -
2017 Oral: Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes »
Taylor Killian · Samuel Daulton · Finale Doshi-Velez · George Konidaris -
2015 Workshop: Machine Learning From and For Adaptive User Technologies: From Active Learning & Experimentation to Optimization & Personalization »
Joseph Jay Williams · Yasin Abbasi Yadkori · Finale Doshi-Velez -
2015 Poster: Mind the Gap: A Generative Approach to Interpretable Feature Selection and Extraction »
Been Kim · Julie A Shah · Finale Doshi-Velez