# Publications Search Within Results Search Within Results search ## 224 results Show filters filter\_alt Sort by Year of PublicationAlphabetical A-Z sort ## 224 results Download 224 citations download- [BibTeX](/node/719106/export?format=bibtex) - [EndNote X3 XML](/node/719106/export?format=endnote8) - [EndNote 7 XML](/node/719106/export?format=endnote7) - [Endnote tagged](/node/719106/export?format=tagged) - [Marc](/node/719106/export?format=marc) - [PubMedId](/node/719106/export?format=pubmed_id) - [RIS](/node/719106/export?format=ris) ### 2023 Fu H, Yao J, Gottesman O, Doshi-Velez F, Konidaris G. [Performance Bounds for Model and Policy Transfer in Hidden-parameter MDPs](/publications/performance-bounds-model-and-policy-transfer-hidden-parameter-mdps). In: The Eleventh International Conference on Learning Representations. 2023. Fu H, Yao J, Gottesman O, Doshi-Velez F, Konidaris G. [Performance Bounds for Model and Policy Transfer in Hidden-parameter MDPs](/publications/performance-bounds-model-and-policy-transfer-hidden-parameter-mdps). In: The Eleventh International Conference on Learning Representations. 2023. - add\_circle\_outline do\_not\_disturb\_on Abstract - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/fu_et_al._-_2023_-_performance_bounds_for_model_and_policy_transfer_i.pdf) - [ descriptionPublisher's Version](https://openreview.net/forum?id=20gBzEzgtiI) In the Hidden-Parameter MDP (HiP-MDP) framework, a family of reinforcement learning tasks is generated by varying hidden parameters specifying the dynamics and reward function for each individual task. HiP-MDP is a natural model for families of tasks in... - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/fu_et_al._-_2023_-_performance_bounds_for_model_and_policy_transfer_i.pdf) - [ descriptionPublisher's Version](https://openreview.net/forum?id=20gBzEzgtiI) Sharma A, Parbhoo S, Gottesman O, Doshi-Velez F. [Robust Decision-Focused Learning for Reward Transfer](/publications/robust-decision-focused-learning-reward-transfer). Preprint. 2023. doi:10.48550/arXiv.2304.03365 Sharma A, Parbhoo S, Gottesman O, Doshi-Velez F. [Robust Decision-Focused Learning for Reward Transfer](/publications/robust-decision-focused-learning-reward-transfer). Preprint. 2023. doi:10.48550/arXiv.2304.03365 - add\_circle\_outline do\_not\_disturb\_on Abstract - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/sharma_et_al._-_2023_-_robust_decision-focused_learning_for_reward_transf.pdf) - [ descriptionPublisher's Version](http://arxiv.org/abs/2304.03365) Decision-focused (DF) model-based reinforcement learning has recently been introduced as a powerful algorithm which can focus on learning the MDP dynamics which are most relevant for obtaining high rewards. While this approach increases the performance of... - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/sharma_et_al._-_2023_-_robust_decision-focused_learning_for_reward_transf.pdf) - [ descriptionPublisher's Version](http://arxiv.org/abs/2304.03365) Sharma A, Zhang J, Nikovski D, Doshi-Velez F. [Travel-time prediction using neural-network-based mixture models](/publications/travel-time-prediction-using-neural-network-based-mixture-models). The 14th International Conference on Ambient Systems, Networks and Technologies Networks (ANT 2022) and The 6th International Conference on Emerging Data and Industry 4.0 (EDI40). 2023;220:1033–1038. doi:10.1016/j.procs.2023.03.144 Sharma A, Zhang J, Nikovski D, Doshi-Velez F. [Travel-time prediction using neural-network-based mixture models](/publications/travel-time-prediction-using-neural-network-based-mixture-models). The 14th International Conference on Ambient Systems, Networks and Technologies Networks (ANT 2022) and The 6th International Conference on Emerging Data and Industry 4.0 (EDI40). 2023;220:1033–1038. doi:10.1016/j.procs.2023.03.144 - add\_circle\_outline do\_not\_disturb\_on Abstract - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/sharma_et_al._-_2023_-_travel-time_prediction_using_neural-network-based_.pdf) - [ descriptionPublisher's Version](https://www.sciencedirect.com/science/article/pii/S1877050923006798) Accurate estimation of travel times is an important step in smart transportation and smart building systems. Poor estimation of travel times results in both frustrated users and wasted resources. Current methods that estimate travel times usually only... - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/sharma_et_al._-_2023_-_travel-time_prediction_using_neural-network-based_.pdf) - [ descriptionPublisher's Version](https://www.sciencedirect.com/science/article/pii/S1877050923006798) Sharma A, Parbhoo S, Gottesman O, Doshi-Velez F. [Robust Decision-Focused Learning for Reward Transfer](/publications/robust-decision-focused-learning-reward-transfer-0). 2023. doi:10.48550/arXiv.2304.03365 Sharma A, Parbhoo S, Gottesman O, Doshi-Velez F. [Robust Decision-Focused Learning for Reward Transfer](/publications/robust-decision-focused-learning-reward-transfer-0). 2023. doi:10.48550/arXiv.2304.03365 - add\_circle\_outline do\_not\_disturb\_on Abstract - [ descriptionPublisher's Version](http://arxiv.org/abs/2304.03365) Decision-focused (DF) model-based reinforcement learning has recently been introduced as a powerful algorithm which can focus on learning the MDP dynamics which are most relevant for obtaining high rewards. While this approach increases the performance of... - [ descriptionPublisher's Version](http://arxiv.org/abs/2304.03365) ### 2022 Chin Z, Raval S, Doshi-Velez F, Wattenberg M, Celi LA. [Identifying Structure in the MIMIC ICU Dataset](/publications/identifying-structure-mimic-icu-dataset). In: Preprint. Proceedings of the Conference on Health, Inference, and Learning, 2022. ; 2022. Chin Z, Raval S, Doshi-Velez F, Wattenberg M, Celi LA. [Identifying Structure in the MIMIC ICU Dataset](/publications/identifying-structure-mimic-icu-dataset). In: Preprint. Proceedings of the Conference on Health, Inference, and Learning, 2022. ; 2022. - add\_circle\_outline do\_not\_disturb\_on Abstract - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/chin_et_al._-_2022_-_identifying_structure_in_the_mimic_icu_dataset.pdf) - [ descriptionPublisher's Version](https://openreview.net/forum?id=3vfn-cmUYQF) The MIMIC-III dataset, containing trajectories of 40,000 ICU patients, is one of the most popular datasets in machine learning for health space. However, there has been very little systematic exploration to understand what is the natural structure of... - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/chin_et_al._-_2022_-_identifying_structure_in_the_mimic_icu_dataset.pdf) - [ descriptionPublisher's Version](https://openreview.net/forum?id=3vfn-cmUYQF) Chen Z, Subhash V, Havasi M, Pan W, Doshi-Velez F. [What Makes a Good Explanation?: A Harmonized View of Properties of Explanations](/publications/what-makes-good-explanation-harmonized-view-properties-explanations). In: Workshop on Trustworthy and Socially Responsible Machine Learning, NeurIPS 2022. 2022. Chen Z, Subhash V, Havasi M, Pan W, Doshi-Velez F. [What Makes a Good Explanation?: A Harmonized View of Properties of Explanations](/publications/what-makes-good-explanation-harmonized-view-properties-explanations). In: Workshop on Trustworthy and Socially Responsible Machine Learning, NeurIPS 2022. 2022. - add\_circle\_outline do\_not\_disturb\_on Abstract - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/chen_et_al._-_2022_-_what_makes_a_good_explanation_a_harmonized_view_.pdf) - [ descriptionPublisher's Version](https://openreview.net/forum?id=TnFHizNosji) Interpretability provides a means for humans to verify aspects of machine learning (ML) models. Different tasks require explanations with different properties. However, presently, there is a lack of standardization in assessing properties of explanations... - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/chen_et_al._-_2022_-_what_makes_a_good_explanation_a_harmonized_view_.pdf) - [ descriptionPublisher's Version](https://openreview.net/forum?id=TnFHizNosji) Subhash V, Chen Z, Havasi M, Pan W, Doshi-Velez F. [What Makes a Good Explanation?: A Harmonized View of Properties of Explanations](/publications/what-makes-good-explanation-harmonized-view-properties-explanations-0). In: Progress and Challenges in Building Trustworthy Embodied AI. 2022. Subhash V, Chen Z, Havasi M, Pan W, Doshi-Velez F. [What Makes a Good Explanation?: A Harmonized View of Properties of Explanations](/publications/what-makes-good-explanation-harmonized-view-properties-explanations-0). In: Progress and Challenges in Building Trustworthy Embodied AI. 2022. - add\_circle\_outline do\_not\_disturb\_on Abstract - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/subhash_et_al._-_2022_-_what_makes_a_good_explanation_a_harmonized_view_.pdf) - [ description Publisher's Version](https://openreview.net/forum?id=YDyLZWwpBK2) Interpretability provides a means for humans to verify aspects of machine learning (ML) models. Different tasks require explanations with different properties. However, presently, there is a lack of standardization in assessing properties of explanations... - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/subhash_et_al._-_2022_-_what_makes_a_good_explanation_a_harmonized_view_.pdf) - [ description Publisher's Version](https://openreview.net/forum?id=YDyLZWwpBK2) Zhang K, Wang H, Du J, Chu B, Robles Arévalo A, Kindle R, Celi LA, Doshi-Velez F. [An interpretable RL framework for pre-deployment modeling in ICU hypotension management](/publications/interpretable-rl-framework-pre-deployment-modeling-icu-hypotension-management). npj Digital Medicine. 2022;5(1):1–10. doi:10.1038/s41746-022-00708-4 Zhang K, Wang H, Du J, Chu B, Robles Arévalo A, Kindle R, Celi LA, Doshi-Velez F. [An interpretable RL framework for pre-deployment modeling in ICU hypotension management](/publications/interpretable-rl-framework-pre-deployment-modeling-icu-hypotension-management). npj Digital Medicine. 2022;5(1):1–10. doi:10.1038/s41746-022-00708-4 - add\_circle\_outline do\_not\_disturb\_on Abstract - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/zhang_et_al._-_2022_-_an_interpretable_rl_framework_for_pre-deployment_m.pdf) - [ descriptionPublisher's Version](https://www.nature.com/articles/s41746-022-00708-4) Computational methods from reinforcement learning have shown promise in inferring treatment strategies for hypotension management and other clinical decision-making challenges. Unfortunately, the resulting models are often difficult for clinicians to... - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/zhang_et_al._-_2022_-_an_interpretable_rl_framework_for_pre-deployment_m.pdf) - [ descriptionPublisher's Version](https://www.nature.com/articles/s41746-022-00708-4) Yacoby Y, Green B, Jr CLG, Doshi-Velez F. [“If it didn’t happen, why would I change my decision?”: How Judges Respond to Counterfactual Explanations for the Public Safety Assessment](/publications/%E2%80%9Cif-it-didn%E2%80%99t-happen-why-would-i-change-my-decision%E2%80%9D-how-judges-respond). Proceedings of the AAAI Conference on Human Computation and Crowdsourcing. 2022;10:219–230. doi:10.1609/hcomp.v10i1.22001 Yacoby Y, Green B, Jr CLG, Doshi-Velez F. [“If it didn’t happen, why would I change my decision?”: How Judges Respond to Counterfactual Explanations for the Public Safety Assessment](/publications/%E2%80%9Cif-it-didn%E2%80%99t-happen-why-would-i-change-my-decision%E2%80%9D-how-judges-respond). Proceedings of the AAAI Conference on Human Computation and Crowdsourcing. 2022;10:219–230. doi:10.1609/hcomp.v10i1.22001 - add\_circle\_outline do\_not\_disturb\_on Abstract - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/yacoby_et_al._-_2022_-_if_it_didnt_happen_why_would_i_change_my_decisi.pdf) - [ descriptionPublisher's Version](https://ojs.aaai.org/index.php/HCOMP/article/view/22001) Many researchers and policymakers have expressed excitement about algorithmic explanations enabling more fair and responsible decision-making. However, recent experimental studies have found that explanations do not always improve human use of algorithmic... - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/yacoby_et_al._-_2022_-_if_it_didnt_happen_why_would_i_change_my_decisi.pdf) - [ descriptionPublisher's Version](https://ojs.aaai.org/index.php/HCOMP/article/view/22001) Liao QV, Zhang Y, Luss R, Doshi-Velez F, Dhurandhar A. [Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI](/publications/connecting-algorithmic-research-and-usage-contexts-perspective-contextualized). Proceedings of the AAAI Conference on Human Computation and Crowdsourcing. 2022;10:147–159. doi:10.1609/hcomp.v10i1.21995 Liao QV, Zhang Y, Luss R, Doshi-Velez F, Dhurandhar A. [Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI](/publications/connecting-algorithmic-research-and-usage-contexts-perspective-contextualized). Proceedings of the AAAI Conference on Human Computation and Crowdsourcing. 2022;10:147–159. doi:10.1609/hcomp.v10i1.21995 - add\_circle\_outline do\_not\_disturb\_on Abstract - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/liao_et_al._-_2022_-_connecting_algorithmic_research_and_usage_contexts.pdf) - [ descriptionPublisher's Version](https://ojs.aaai.org/index.php/HCOMP/article/view/21995) Recent years have seen a surge of interest in the field of explainable AI (XAI), with a plethora of algorithms proposed in the literature. However, a lack of consensus on how to evaluate XAI hinders the advancement of the field. We highlight that XAI is... - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/liao_et_al._-_2022_-_connecting_algorithmic_research_and_usage_contexts.pdf) - [ descriptionPublisher's Version](https://ojs.aaai.org/index.php/HCOMP/article/view/21995) Lage I, Pradier MF, McCoy TH, Perlis RH, Doshi-Velez F. [Do clinicians follow heuristics in prescribing antidepressants?](/publications/do-clinicians-follow-heuristics-prescribing-antidepressants) Journal of Affective Disorders. 2022;311:110–114. doi:10.1016/j.jad.2022.04.128 Lage I, Pradier MF, McCoy TH, Perlis RH, Doshi-Velez F. [Do clinicians follow heuristics in prescribing antidepressants?](/publications/do-clinicians-follow-heuristics-prescribing-antidepressants) Journal of Affective Disorders. 2022;311:110–114. doi:10.1016/j.jad.2022.04.128 - add\_circle\_outline do\_not\_disturb\_on Abstract - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/1-s2.0-s0165032722004724-main.pdf) - [ descriptionPublisher's Version](https://www.sciencedirect.com/science/article/pii/S0165032722004724) Background While clinicians commonly learn heuristics to guide antidepressant treatment selection, surveys suggest real-world prescribing practices vary widely. We aimed to determine the extent to which antidepressant prescriptions were consistent with... - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/1-s2.0-s0165032722004724-main.pdf) - [ descriptionPublisher's Version](https://www.sciencedirect.com/science/article/pii/S0165032722004724) Penrod M, Termotto H, Reddy V, Yao J, Doshi-Velez F, Pan W. [Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry](/publications/success-uncertainty-aware-deep-models-depends-data-manifold-geometry). Preprint. 2022. doi:10.48550/arXiv.2208.01705 Penrod M, Termotto H, Reddy V, Yao J, Doshi-Velez F, Pan W. [Success of Uncertainty-Aware Deep Models Depends on Data Manifold Geometry](/publications/success-uncertainty-aware-deep-models-depends-data-manifold-geometry). Preprint. 2022. doi:10.48550/arXiv.2208.01705 - add\_circle\_outline do\_not\_disturb\_on Abstract - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/penrod_et_al._-_2022_-_success_of_uncertainty-aware_deep_models_depends_o.pdf) - [ descriptionPublisher's Version](http://arxiv.org/abs/2208.01705) For responsible decision making in safety-critical settings, machine learning models must effectively detect and process edge-case data. Although existing works show that predictive uncertainty is useful for these tasks, it is not evident from literature... - [ picture\_as\_pdfPaper](/sites/g/files/omnuum4281/files/finale/files/penrod_et_al._-_2022_-_success_of_uncertainty-aware_deep_models_depends_o.pdf) - [ descriptionPublisher's Version](http://arxiv.org/abs/2208.01705) - Previous page chevron\_left - [1](?page=0 "Current page") - [2](?page=1 "Go to page 2") - [3](?page=2 "Go to page 3") - [ Last page 19 ](?page=18 "Go to last page") - [ Next page chevron\_right ](?page=1 "Go to next page")