Recent Publications
You can find DtAK publications from past years at Finale's Google Scholar profile.
Mitigating the Effects of Non-Identifiability on Inference for Bayesian Neural Networks with Latent Variables
JMLR, 2022 [pdf]
"If it didn’t happen, why would I change my decision?": How Judges Respond to Counterfactual Explanations for the Public Safety Assessment
HCOMP 2022 and CHI Workshop on Human Centered Explainable AI (HCXAI), 2022 [pdf]
Generalizing Off-Policy Evaluation From a Causal Perspective For Sequential Decision-Making
Preprint, 2022 [pdf]
Learning Predictive and Interpretable Timeseries Summaries from ICU Data
In Proceedings of AMIA Annual Symposium, 2021 [pdf]
On formalizing causal off-policy evaluation for sequential decision-making
proceedings at the International Conference on Machine Learning: Workshop on Neglected Assumptions in Causal Inference, 2021
Pre-emptive Learning to Defer for Sequential Medical Decision-Making Under Uncertainty
proceedings at the International Conference on Machine Learning: Workshop on Interpretable Machine Learning for Healthcare, 2021 [pdf]
Optimizing for Interpretability in Deep Neural Networks with Tree Regularization
Journal of AI Research (JAIR), 2021 [pdf]
Promises and Pitfalls of Black-Box Concept Learning Models
proceedings at the Internation Conference on Machine Learning: Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI, 2021 [pdf]
Wide Mean-Field Variational Bayesian Neural Networks Ignore the Data
proceedings at the International Conference on Machine Learning: Workshop on Uncertainty & Robustness in Deep Learning (ICML), 2021 [pdf]
Prediction-focused Mixture Models
proceedings at the International Conference on Machine Learning: Information-Theoretic Methods for Rigorous, Responsible, and Reliable Machine Learning (ICML), 2021 [pdf]
Generalization in Clinical Prediction Models: The Blessing and Curse of Measurement Indicator Variables
Critical Care Explorations, 2021 [pdf]
Power Constrained Bandit
proceedings at the Machine Learning for Healthcare Conference, 2021 [pdf]
Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning
Preprint, 2021 [pdf]
Designing AI for Trust and Collaboration in Time-Constrained Medical Decisions: A Sociotechnical Lens
proceedings at the 2021 CHI Conference on Human Factors in Computing Systems, 2021 [pdf]
Evaluating the Interpretability of Generative Models by Interactive Reconstruction
proceedings at the 2021 CHI Conference on Human Factors in Computing Systems, 2021 [pdf]
Machine Learning Techniques for Accountability
AI Magazine, 2021 [pdf]
Learning Under Adversarial and Interventional Shifts
Preprint, 2021 [pdf]
Depth-Bounded Statistical PCFG Induction as a Model of Human Grammar Acquisition
Computational Linguistics, 2021 [pdf]
Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement
Preprint, 2021 [pdf]
How machine-learning recommendations influence clinician treatment selections: the example of antidepressant selection
Translational psychiatry, 2021 [pdf]
Preferential Mixture-of-Experts: Interpretable Models that Rely on Human Expertise As Much As Possible
Proceedings of Clinical Research Informatics AMIA Summit, 2021 [pdf]
Predicting change in diagnosis from major depression to bipolar disorder after antidepressant initiation
Neuropsychopharmacology, 2021 [pdf]
Identifying Decision Points for Safe and Interpretable Reinforcement Learning in Hypotension Treatment
proceedings at the Neural Information Processing Systems Workshop on Machine Learning for Health, 2020 [pdf]
Shaping Control Variates for Off-Policy Evaluation
proceedings at Neural Information Processing Systems Workshop on Offline Reinforcement Learning, 2020
Artificial Intelligence & Cooperation
Preprint, 2020 [pdf]
Learning Interpretable Concept-Based Models with Human Feedback
proceedings at the International Conference on Machine Learning: Workshop on Human Interpretability in Machine Learning, 2020 [pdf]
Interpretable off-policy evaluation in reinforcement learning by highlighting influential transitions
proceedings at the International Conference on Machine Learning, 2020 [pdf]
Incorporating Interpretable Output Constraints in Bayesian Neural Networks
proceedings at the Conference on Neural Information Processing Systems, 2020 [pdf]
Transfer learning from well-curated to less-resourced populations with hiv
proceedings at the Machine Learning for Health Care Conference, 2020 [pdf]
The myth of generalisability in clinical research and machine learning in health care
The Lancet Digital Health, 2020 [pdf]
PoRB-Nets: Poisson Process Radial Basis Function Networks
proceedings at the Conference on Uncertainty in Artificial Intelligence, 2020 [pdf]
Failures of Variational Autoencoders and their Effects on Downstream Tasks
proceedings at the International Conference on Machine Learning: Workshop on Uncertainty & Robustness in Deep Learning (ICML), 2020 [pdf]
CRUDS: Counterfactual Recourse Using Disentangled Subspaces
proceedings at the International Conference on Machine Learning: Workshop on Human Interpretability in Machine Learning, 2020 [pdf]
BaCOUn - Bayesian Classifers with Out-of-Distribution Uncertainty
proceedings at the International Conference on Machine Learning: Workshop on Uncertainty & Robustness in Deep Learning (ICML), 2020 [pdf]
Amortised Variational Inference for Hierarchical Mixture Models
proceedings at the International Conference on Machine Learning: Workshop on Uncertainty & Robustness in Deep Learning (ICML), 2020 [pdf]
Learned Uncertainty-Aware (LUNA) Bases for Bayesian Regression using Multi-Headed Auxiliary Networks
proceedings at the International Conference on Machine Learning: Workshop on Uncertainty & Robustness in Deep Learning (ICML), 2020 [pdf]
Power-Constrained Bandit
arXiv:2004.06230, 2020 [pdf]
Characterizing and Avoiding Problematic Global Optima of Variational Autoencoders
Advances in Approximate Bayesian Inference, 2019 [pdf]
Defining Admissible Rewards for High-Confidence Policy Evaluation in Batch Reinforcement Learning
ACM Conference on Health, Inference and Learning, 2020 [pdf]
Prediction Focused Topic Models via Feature Selection
AISTATS, 2020 [pdf]
POPCORN: Partially Observed Prediction Constrained Reinforcement Learning
AISTATS, 2020 [pdf]
Regional Tree Regularization for Interpretability in Deep Neural Networks
AAAI, 2020 [pdf]
Identifying Distinct, Effective Treatments for Acute Hypotension with SODA-RL: Safely Optimized Diverse Accurate Reinforcement Learning
AMIA CRI, 2020 [pdf]
Interpretable Batch IRL to extract clinician goals in ICU Hypotension Management
AMIA CRI, 2020 [pdf]
Big Data in the Assessment of Pediatric Medication Safety
Pediatrics, 2020 [pdf]
Evaluating Machine Learning Articles
JAMA, 2020 [pdf]
Predicting treatment dropout after antidepressant initiation
Translational Psychiatry, 2020 [pdf]