Recent Publications

You can find DtAK publications from past years at Finale's Google Scholar profile.

"If it didn’t happen, why would I change my decision?": How Judges Respond to Counterfactual Explanations for the Public Safety Assessment
Y Yacoby, B Green, C L Griffin, F Doshi-Velez
Generalizing Off-Policy Evaluation From a Causal Perspective For Sequential Decision-Making
S Parbhoo, S Joshi, F Doshi-Velez
Learning Predictive and Interpretable Timeseries Summaries from ICU Data
N Johnson, S Parbhoo, A Ross, F Doshi-Velez
On formalizing causal off-policy evaluation for sequential decision-making
S Parbhoo *, S Joshi *
Pre-emptive Learning to Defer for Sequential Medical Decision-Making Under Uncertainty
S Joshi *, S Parbhoo *, F Doshi-Velez
Optimizing for Interpretability in Deep Neural Networks with Tree Regularization
M Wu, S Parbhoo, M Hughes, V Roth, F Doshi-Velez
Promises and Pitfalls of Black-Box Concept Learning Models
A Mahinpei, J Clark, I Lage, F Doshi-Velez, W Pan
Wide Mean-Field Variational Bayesian Neural Networks Ignore the Data
B Coker, W Pan, F Doshi-Velez
Prediction-focused Mixture Models
S Narayanan *, A Sharma *, C Zeng, F Doshi-Velez
Generalization in Clinical Prediction Models: The Blessing and Curse of Measurement Indicator Variables
J Futoma, M Simons, F Doshi-Velez, R Kamaleswaran
Power Constrained Bandit
J Yao, E Brunskill, W Pan, S Murphy, F Doshi-Velez
Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning
K Wang, S Shat, H Chen, A Perrault, F Doshi-Velez, M Tambe
Designing AI for Trust and Collaboration in Time-Constrained Medical Decisions: A Sociotechnical Lens
M Jacobs, J He, M F. Pradier, B Lam, A C Ahn, T H McCoy, R H Perlis, F Doshi-Velez, K Z Gajos
Evaluating the Interpretability of Generative Models by Interactive Reconstruction
A Ross, N Chen, EZ Hang, EL Glassman, F Doshi-Velez
Machine Learning Techniques for Accountability
B Kim, F Doshi-Velez
Learning Under Adversarial and Interventional Shifts
H Singh, S Joshi, F Doshi-Velez, H Lakkaraju
Depth-Bounded Statistical PCFG Induction as a Model of Human Grammar Acquisition
L Jin, L Schwartz, F Doshi-Velez, T Miller, W Schuler
Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement
AS Ross, F Doshi-Velez
How machine-learning recommendations influence clinician treatment selections: the example of antidepressant selection
M Jacobs, MF Pradier, TH McCoy, RH Perlis, F Doshi-Velez, KZ Gajos
Preferential Mixture-of-Experts: Interpretable Models that Rely on Human Expertise As Much As Possible
MF Pradier, J Zazo, S Parbhoo, RH Perlis, M Zazzi, F Doshi-Velez
Predicting change in diagnosis from major depression to bipolar disorder after antidepressant initiation
M F Pradier, M C Hughes, T H McCoy, S A Barroilhet, F Doshi-Velez, R H Perlis
Identifying Decision Points for Safe and Interpretable Reinforcement Learning in Hypotension Treatment
K Zhang, Y Wang, J Du, B Chu, LA Celi, R Kindle, F Doshi-Velez
Shaping Control Variates for Off-Policy Evaluation
S Parbhoo, O Gottesman, F Doshi-Velez
Artificial Intelligence & Cooperation
E Bertino, F Doshi-Velez, M Gini, D Lopresti, D Parkes
Learning Interpretable Concept-Based Models with Human Feedback
I Lage, F Doshi-Velez
Interpretable off-policy evaluation in reinforcement learning by highlighting influential transitions
O Gottesman, J Futoma, Y Liu, S Parbhoo, L Celi, E Brunskill, F Doshi-Velez
Incorporating Interpretable Output Constraints in Bayesian Neural Networks
W Yang, L Lorch, MA Graule, H Lakkaraju, F Doshi-Velez
Transfer learning from well-curated to less-resourced populations with hiv
S Parbhoo, M Wieser, V Roth, F Doshi-Velez
The myth of generalisability in clinical research and machine learning in health care
J Futoma, M Simons, T Panch, F Doshi-Velez, LA Celi
PoRB-Nets: Poisson Process Radial Basis Function Networks
B Coker, MF Pradier, F Doshi-Velez
Failures of Variational Autoencoders and their Effects on Downstream Tasks
Yacoby Y, Pan W, Doshi-Velez F
CRUDS: Counterfactual Recourse Using Disentangled Subspaces
M Downs, J Chu, Y Yacoby, F Doshi-Velez, W Pan
BaCOUn - Bayesian Classifers with Out-of-Distribution Uncertainty
Guenais T, Vamvourellis D, Yacoby Y, Doshi-Velez F, Pan W
Amortised Variational Inference for Hierarchical Mixture Models
J Antorán, J Yao, W Pan, F Doshi-Velez, JM Hernández-Lobato
Learned Uncertainty-Aware (LUNA) Bases for Bayesian Regression using Multi-Headed Auxiliary Networks
Thakur S, Lorsung C, Yacoby Y, Doshi-Velez F, Pan W
Power-Constrained Bandit
Yao J, Brunskill E, Pan W, Murphy S, Doshi-Velez F
Characterizing and Avoiding Problematic Global Optima of Variational Autoencoders
Yacoby Y, Pan W, Doshi-Velez F
Defining Admissible Rewards for High-Confidence Policy Evaluation in Batch Reinforcement Learning
Prasad N, Engelhardt B, Doshi-Velez F
Prediction Focused Topic Models via Feature Selection
Ren J, Kunes R, Doshi-Velez F
POPCORN: Partially Observed Prediction Constrained Reinforcement Learning
Futoma J, Hughes M, Doshi-Velez F
Regional Tree Regularization for Interpretability in Deep Neural Networks
Wu M, Parbhoo S, Hughes M, Kindle R, Celi L, Zazzi M, Volker R, Doshi-Velez F
Ensembles of Locally Independent Prediction Models
Ross A, Pan W, Celi L, Doshi-Velez F
Identifying Distinct, Effective Treatments for Acute Hypotension with SODA-RL: Safely Optimized Diverse Accurate Reinforcement Learning
Futoma F, Masgood M, Doshi-Velez F
Interpretable Batch IRL to extract clinician goals in ICU Hypotension Management
Srinivasan S, Doshi-Velez F
Big Data in the Assessment of Pediatric Medication Safety
McMahon A, Cooper W, Brown J, Carleton B, Doshi-Velez F, Kohane I, Goldman J, Hoffman M, Kamaleswaran R, Sakiyama M, et al.
Evaluating Machine Learning Articles
Doshi-Velez F, Perlis R
Predicting treatment dropout after antidepressant initiation
Pradier M, McCoy T, Hughes M, Perlis R, Doshi-Velez F