Finale Doshi-Velez

Interests

I head the Data to Actionable Knowledge (DtAK) group at Harvard Computer Science. We use probabilistic methods to address many decision-making scenarios, with a focus on applications related to healthcare. Our work falls into three major areas:

Probabilistic modeling and inference (especially Bayesian models): How can we characterize the uncertainty in large, heterogeneous data? How can we fit models that will be useful for downstream decision-making? How can we build models and inference techniques that will behave in expected and desired ways?

Decision-making under uncertainty (especially sequential decision-making): How can we optimize policies given batches of heterogeneous data? How can we provide useful information, even if we can't solve for a policy? How can we characterize the limits of our ability to provide decision support?

Interpretability and Statistical methods for validation: How can we estimate the quality of a policy from batch data? How can we expose key elements of a model or policy for expert inspection?

Short Bio

Finale Doshi-Velez is a John L. Loeb associate professor in Computer Science at the Harvard Paulson School of Engineering and Applied Sciences. She completed her MSc from the University of Cambridge as a Marshall Scholar, her PhD from MIT, and her postdoc at Harvard Medical School. Her interests lie at the intersection of machine learning, healthcare, and interpretablity.

Selected Additional Shinies: AFOSR YIP and NSF CAREER recipient; Sloan Fellow; IEEE AI Top 10 to Watch

Publications

2019

Gottesman O, Johansson F, Komorowski M, Faisal A, Sontag D, Doshi-Velez F, Celi L. Guidelines for reinforcement learning in healthcare. Nature Medicine. 2019;25 :16-18. Paper

2018

• Lage I, Chen E, He J, Narayanan M, Gershman S, Kim B, Doshi-Velez F. An Evaluation of the Human-Interpretability of Explanation. Conference on Neural Information Processing Systems (NeurIPS) Workshop on Correcting and Critiquing Trends in Machine Learning. 2018. Paper
• Pradier MF, Pan W, Yao J, Ghosh S, Doshi-Velez F. Projected BNNs: Avoiding weight-space pathologies by projecting neural network weights. Conference on Neural Information Processing Systems (NeurIPS) Workshop on Bayesian Deep Learning . 2018. Paper
• Fernandez-Pradier M, Pan W, Yao M, Singh R, Doshi-Velez F. Hierarchical Stick-breaking Feature Paintbox. Conference on Neural Information Processing Systems (NeurIPS) Workshop on All of Bayesian Nonparametrics. 2018. Paper
• Futoma J, Hughes MC, Doshi-Velez F. Prediction-Constrained POMDPs. Conference on Neural Information Processing Systems (NeurIPS) Workshop on Reinforcement Learning under Partial Observability . 2018. Paper
• Parbhoo S, Gottesman O, Ross AS, Komorowski M, Faisal A, Bon I, Roth V, Doshi-Velez F. Improving counterfactual reasoning with kernelised dynamic mixing models. PLoS ONE . 2018;13 (11). Paper
• Lage I, Ross A, Kim B, Gershman S, Doshi-Velez F. Human-in-the-Loop Interpretability Prior. Conference on Neural Information Processing Systems (NeurIPS). 2018. Paper
• Wu M, Hughes M, Parbhoo S, Zazzi M, Roth V, Doshi-Velez F. Beyond Sparsity: Tree Regularization of Deep Models for Interpretability. Association for the Advancement of Artificial Intelligence (AAAI). 2018. Paper
• Masood MA, Doshi-Velez F. Diversity-Inducing Policy Gradient: Using MMD to find a set of policies that are diverse in terms of stete-visitation. International Conference on Machine Learning (ICML) Exploration in Reinforcement Learning Workshop. 2018. Paper
• Peng X, Ding Y, Wihl D, Gottesman O, Komorowski M, Lehman L-wei H, Ross A, Faisal A, Doshi-Velez F. Improving Sepsis Treatment Strategies by Combining Deep and Kernel-Based Reinforcement Learning. American Medical Informatics Association (AMIA) Annual Symposium. 2018. Paper
• Ghosh S, Yao J, Doshi-Velez F. Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors, in Proceedings of the 35th International Conference on Machine Learning (ICML). Vol 80. Stockholm, Sweden ; 2018. Paper
• Depeweg S, Hernandez-Lobato JM, Doshi-Velez F, Udluft S. Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning, in Proceedings of the 35th International Conference on Machine Learning (ICML). Vol 80. Stockholm, Sweden ; 2018. Paper
• Gottesman O, Pan W, Doshi-Velez F. Weighted Tensor Decomposition for Learning Latent Variables with Partial Data, in Proceedings of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS) 2018. Vol 84. Lanzarote, Spain ; 2018. Paper
• Hughes MC, Hope G, Weiner L, Thomas H. McCoy J, Perlis RH, Sudderth E, Doshi-Velez F. Semi-Supervised Prediction-Constrained Topic Models, in Proceedings of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS) 2018. Vol 84. Lanzarote, Spain ; 2018. Paper
• Amir O, Doshi-Velez F, Sarne D. Agent Strategy Summarization. Autonomous Agents and Multiagent Systems, Blue Sky Ideas Track. 2018. Paper
• Doshi-Velez F, Kortz M, Budish R, Bavitz C, Gershman S, O'Brien D, Shieber S, Waldo J, Weinberger D, Wood A. Accountability of AI Under the Law: The Role of Explanation. Privacy Law Scholars Conference. 2018. Paper
• Jin L, Doshi-Velez F, Miller T, Schuler W, Schwartz L. Unsupervised Grammar Induction with Depth-bounded PCFG. Association for Computational Linguistics. 2018. Paper
• Ross AS, Doshi-Velez F. Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients. Association for the Advancement of Artificial Intelligence (AAAI). 2018. Paper
• Yao J, Killian T, Konidaris G, Doshi-Velez F. Direct Policy Transfer via Hidden Parameter Markov Decision Processes. International Conference on Machine Learning (ICML) Workshop on Lifelong Learning,. 2018. Paper
• Raghu A, Gottesman O, Liu Y, Komorowski M, Faisal A, Doshi-Velez F, Brunskill E. Behaviour Policy Estimation in Off-Policy Policy Evaluation: Calibration Matters. International Conference on Machine Learning (ICML) Workshop on CausalML. 2018. Paper
• Pages
• Sussex S, Gottesman O, Liu Y, Murphy S, Brunskill E, Doshi-Velez F. Stitched Trajectories for Off-Policy Learning. International Conference on Machine Learning (ICML) Workshop on CausalML,. 2018. Paper
• Liu Y, Gottesman O, Raghu A, Komorowski M, Faisal A, Doshi-Velez F, Brunskill E. Representation Balancing MDPs for Off-Policy Policy Evaluation. International Conference on Machine Learning (ICML) Workshop on CausalML. 2018. Paper
• Gottesman O, Doshi-Velez F. Regularizing Tensor Decomposition Methods by Optimizing Pseudo-Data. International Conference on Machine Learning (ICML) Exploration in Reinforcement Learning Workshop,. 2018. Paper
• Ross AS, Pan W, Doshi-Velez F. Learning Qualitatively Diverse and Interpretable Rules for Classification. International Conference on Machine Learning (ICML) Workshop on Human Interpretability in Machine Learning,. 2018. Paper
• Jin L, Doshi-Velez F, Miller T, Schuler W, Schwartz L. Depth-bounding is effective: Improvements and Evaluation of Unsupervised PCFG Induction. Conference on Empirical Methods in Natural Language Processing (EMNLP) . 2018. Paper
• Doshi-Velez F, Kim B. Considerations for Evaluation and Generalization in Interpretable Machine Learning. In: Escalante H, Escalera S, Guyon I, Baró X, Güçlütürk Y, Güçlü U, van Gerven MAJ Explainable and Interpretable Models in Computer Vision and Machine Learning. 1st ed. Springer International Publishing ; 2018. Chapter
• Glueck M, Naeini MP, Doshi-Velez F, Chevalier F, Khan A, Wigdor D, Brudno M. PhenoLines: Phenotype Comparison Visualizations for Disease Subtyping via Topic Models. IEEE Transactions on Visualization and Computer Graphics. 2018;24 (1) :371-381. Paper

2017

• Ghassemi M, Wu M, Hughes MC, Szolovits P, Doshi-Velez F. Predicting intervention onset in the ICU with switching state space models. American Medical Informatics Association (AMIA),. 2017. Paper
• Glueck M, Naeini MP, Doshi-Velez F, Chevalier F, Khan A, Wigdor D, Brudno M. PhenoLines: Phenotype Comparison Visualizations for Disease Subtyping via Topic Models. Conference on Visual Analytics Science and Technology (VAST),. 2017. Paper
• Ross AS, Lage I, Doshi-Velez F. The Neural LASSO: Local Linear Sparsity for Interpretable Explanations. Neural Information Processing Systems (NIPS) Workshop on Transparent and Interpretable Machine Learning in Safety Critical Environments. 2017. Paper
• Wu M, Hughes M, Parbhoo S, Zazzi M, Roth V, Doshi-Velez F. Beyond Sparsity: Tree Regularization of Deep Models for Interpretability. Neural Information Processing Systems (NIPS) Workshop on Transparent and Interpretable Machine Learning in Safety Critical Environments. 2017. Paper
• Parbhoo S, Roth V, Doshi-Velez F. Counterfactual Reasoning with Dynamic Switching Models for HIV Therapy Selection. Neural Information Processing Systems (NIPS) Workshop on Machine Learning for Healthcare. 2017. Paper
• Hughes MC, Hope G, Weiner L, McCoy TH, Perlis RH, Sudderth EB, Doshi-Velez F. Prediction-Constrained Topic Models for Antidepressant Recommendation. Neural Information Processing Systems (NIPS) Workshop on Machine Learning for Healthcare. 2017. Paper
• Ghosh S, Doshi-Velez F. Model Selection in Bayesian Neural Networks via Horseshoe Priors. Neural Information Processing Systems (NIPS) Workshop on Bayesian Deep Learning. 2017. Paper
• Singh R, Ling J, Doshi-Velez F. Structured Variational Autoencoders for the Beta-Bernoulli Process. Neural Information Processing Systems (NIPS) Workshop on Advances in Approximate Bayesian Inference. 2017. Paper
• Tan S, Doshi-Velez F, Quiroz J, Glassman E. Clustering LaTeX Solutions to Machine Learning Assignments for Rapid Assessment. Advancing Education with Data Knowledge Discovery and Data Mining (KDD) Workshop. 2017. Paper
• Depeweg S, Hernandez-Lobato JM, Doshi-Velez F, Udluft S. Uncertainty Decomposition in Bayesian Neural Networks with Latent Variables. International Conference on Machine Learning (ICML) Workshop. 2017. Paper
• Parbhoo S, Bogojeska J, Zazzi M, Roth V, Doshi-Velez F. Combining Kernel and Model Based Learning for HIV Therapy Selection, in AMIA Summits on Translational Science Proceedings . Vol 2017. ; 2017 :239. Paper
• Fan A, Doshi-Velez F, Miratrix L. Prior Matters: Simple and General Methods for Evaluating and Improving Topic Quality in Topic Modeling. Text as Data. 2017. Paper
• Killian T, Daulton S, Konidaris G, Doshi-Velez F. Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes. Neural Information Processing Systems (NIPS). 2017. Paper
• Pages
• Wang T, Rudin C, Doshi-Velez F, Liu Y, Klampfl E, MacNeille P. A Bayesian Framework for Learning Rule Sets for Interpretable Classification. Journal of Machine Learning. 2017;18 (70) :1-37. Paper
• Ross AS, Hughes MC, Doshi-Velez F. Right for the Right Reasons: Training Differentiable Models by Constraining their Explananations. International Joint Conference on Artificial Intelligence (IJCAI). 2017. Paper
• Doshi-Velez F, Williamson S. Restricted Indian Buffet Processes. Statistics and Computing. 2017;27 (5) :1205-1223. Paper
• Wu M, Ghassemi M, Fend M, Celi LA, Szolovits P, Doshi-Velez F. Understanding Vasopressor Intervention and Weaning: Risk Prediction in a Public Heterogeneous Clinical Time Series Database. Journal of the American Medical Informatics Association. 2017;24 (3) :488-495.Abstract Paper
• Depewag S, Hernández-Lobato JM, Doshi-Velez F, Udluft S. Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks. ICLR. 2017.Abstract Paper

2016

• Parbhoo S, Bogojeska J, Zazzi M, Roth V, Doshi-Velez F. Combining Kernel and Model Based Learning for HIV Therapy Selection. Neural Information Processing Systems (NIPS) Workshop for Machine Learning and Healthcare. 2016. Paper
• Killian TW, Konidaris G, Doshi-Velez F. Transfer Learning Across Patient Variations with Hidden Parameter Markov Decision Processes. Neural Information Processing Systems (NIPS) Workshop for Machine Learning and Healthcare. 2016. Paper
• Hughes MC, Elibol HM, McCoy T, Perlis R, Doshi-Velez F. Supervised topic models for clinical interpretability. Neural Information Processing Systems (NIPS) Workshop for Machine Learning and Healthcare. 2016. Paper
• Masood MA, Doshi-Velez F. Robust Posterior Exploration in NMF. International Conference on Machine Learning (ICML) Workshop on Geometry in Machine Learning. 2016. Paper
• Shain C, Bryce W, Jin L, Krakovna V, Doshi-Velez F, Miller T, Schuler W, Schwartz L. Memory-Bounded Left-Corner Unsupervised Grammar Induction on Child-Directed Input. Computational Linguistics: Technical Papers (COLING). 2016 :964-975. Paper
• Doshi-Velez F, Konidaris G. Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations. IJCAI. 2016. Paper
• Elibol M, Nguyen V, Linderman S, Johnson M, Hashmi A, Doshi-Velez F. Cross-Corpora Unsupervised Learning of Trajectories in Autism Spectrum Disorders. Journal of Machine Learning Research. 2016;17 (1) :4597-4634. Paper
• Tran D, Kim M, Doshi-Velz F. Spectral M-estimation with Application to Hidden Markov Models: Supplementary Material. AISTATS. 2016. Paper
• Pan W, Doshi-Velez F. A Characterization of the Non-Uniqueness of Nonnegative Matrix Factorizations. arXiv:1604.00653 . 2016.Abstract Paper
• Xia X, Protopapas P, Doshi-Velez F. Cost-Sensitive Batch Mode Active Learning: Designing Astronomical Observation by Optimizing Telescope Time and Telescope Choice. 2016.Abstract Paper
• Masood A, Pan W, Doshi-Velez F. An Empirical Comparison of Sampling Quality Metrics: A Case Study for Bayesian Nonnegative Matrix Factorization. arXiv preprint arXiv:1606.06250. 2016.Abstract Paper
• Gafford J, Doshi-Velez F, Wood R, Walsh C. Machine Learning Approaches to Environmental Disturbance Rejection in Multi-Axis Optoelectronic Force Sensors. Sensors and Actuators A: Physical. 2016;248 :78-87.Abstract Paper
• Lingren T, Chen P, Bochenek J, Doshi-Velez F, Manning-Courtney P, Bickel J, Welchons LW, Reinhold J, Bing N, Ni Y, et al. Electronic Health Record Based Algorithm to Identify Patients with Autism Spectrum Disorder. PLoS ONE 11(7): e0159621. 2016. Paper
• Krakovna V, Doshi-Velez F. Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models. arXiv:1606.05320 . 2016.Abstract Paper

2015

• Wang T, Rudin C, Doshi-Velez F, Liu Y, Klampfl E, MacNeille P. Bayesian Or's of And's for Interpretable Classification with Application to Context Aware Recommender Systems. arXiv:1504.07614. 2015. Paper
• Pages
• Kim B, Shah JA, Doshi-Velez F. Mind the Gap: A Generative Approach to Interpretable Feature Selection and Extraction, in Advances in Neural Information Processing Systems. ; 2015 :2251–2259. Paper
• Doshi-Velez F, Avillach P, Palmer N, Bousvaros A, Ge Y, Fox K, Steinberg G, Spettell C, Juster I, Kohane I. Prevalence of Inflammatory Bowel Disease Among Patients with Autism Spectrum Disorders. Inflammatory bowel diseases. 2015;21 :2281–2288. Paper
• Doshi-Velez F, Pfau D, Wood F, Roy N. Bayesian Nonparametric Methods for Partially-Observable Reinforcement Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence . 2015;37 (2) :394 - 407.Abstract Paper
• Doshi-Velez F, Marshall YE. HackEbola with Data: On the hackathon format for timely data analysis. 2015. Summary Paper
• Doshi-Velez F, Wallace BC, Adams RP. Graph-Sparse LDA: A Topic Model with Structured Sparsity. AAAI . 2015.Abstract Paper

2014

• Doshi-Velez F, Ge Y, Kohane I. Comorbidity clusters in autism spectrum disorders: an electronic health record time-series analysis. Pediatrics. 2014;133 :e54–e63. Paper
• Doshi-Velez F, Wallace B, Adams R. Graph-Sparse LDA: A Topic Model with Structured Sparsity. arXiv:1410.4510. 2014. Paper
• Konidaris G, Doshi-Velez F. Hidden Parameter Markov Decision Processes: An Emerging Paradigm for Modeling Families of Related Tasks. AAAI 2014 Fall Symposium on Knowledge, Skill, and Behavior Transfer in Autonomous Robots. 2014.Abstract Paper
• Ghassemi M, Naumann T, Doshi-Velez F, Brimmer N, Joshi R, Rumshisky A, Szolovits P. Unfolding Physiological State: Mortality Modelling in Intensive Care Units. ACM SIGKDD international conference on Knowledge discovery and data mining. 2014 :75-84 .Abstract Paper

2013

• Doshi-Velez F, Ge Y, Kohane I. Comorbidity Clusters in Autism Spectrum Disorders: An Electronic Health Record Time-Series Analysis. Pediatrics. 2013;10.1542 (peds.2013) :0819.Abstract Paper
• Doshi-Velez F, Konidaris G. Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations. CoRR. 2013;abs/1308.3513.Abstract Paper

2012

• Doshi-Velez F. Bayesian nonparametric approaches for reinforcement learning in partially observable domains. 2012. Thesis
• Doshi-Velez F, Li W, Battat Y, Charrow B, Curthis D, Park J-G, Hemachandra S, Velez J, Walsh C, Fredette D, et al. Improving safety and operational efficiency in residential care settings with WiFi-based localization. Journal of the American Medical Directors Association. 2012;13 :558–563. Paper
• Doshi-Velez F, Konidaris G. Transfer Learning by Discovering Latent Task Parametrizations. the NIPS 2012 Workshop on Bayesian Nonparametric Models for Reliable Planning And Decision-Making Under Uncertainty. 2012. Paper
• Joseph JM, Doshi-Velez F, Roy N. A Bayesian nonparametric approach to modeling battery health. IEEE International Conference on Robotics and Automation. 2012 :1876–1882.Abstract Paper

2011

• Doshi-Velez F, Ghahramani Z. A Comparison of Human and Agent Reinforcement Learning in Partially Observable Domains. 33rd Annual Meeting of the Cognitive Science Society (CogSci). 2011. Paper
• Doshi-Velez F, Roy N. An Analysis of Activity Changes in MS Patients: A Case Study in the Use of Bayesian Nonparametrics. Neural Information Processing Systems (NIPS) Workshop: Bayesian Nonparametrics, Hope or Hype? 2011. Paper
• Joseph JM, Doshi-Velez F, Huang AS, Roy N. A Bayesian nonparametric approach to modeling motion patterns. Auton. Robots. 2011;31 :383–400. Paper
• Doshi F, Wingate D, Tenenbaum JB, Roy N. Infinite Dynamic Bayesian Networks, in Proceedings of the 28th International Conference on Machine Learning. ; 2011 :913–920. Paper
• Geramifard A, Doshi F, Redding J, Roy N, How JP. Online Discovery of Feature Dependencies, in Proceedings of the 28th International Conference on Machine Learning. ; 2011 :881–888. Paper