550 citations · 1k across the 19 of their papers we have counts for
20 papers
Machine Learning for Health symposium 2022 -- Extended Abstract track
Antonio Parziale, Monica Agrawal, Shalmali Joshi +4
A collection of the extended abstracts that were presented at the 2nd Machine Learning for Health symposium (ML4H 2022), which was held both virtually and in person on November 28,…
"Why did the Model Fail?": Attributing Model Performance Changes to Distribution Shifts
Haoran Zhang, Harvineet Singh, Marzyeh Ghassemi +1
Machine learning models frequently experience performance drops under distribution shifts. The underlying cause of such shifts may be multiple simultaneous factors such as changes…
Towards Robust Off-Policy Evaluation via Human Inputs
Harvineet Singh, Shalmali Joshi, Finale Doshi-Velez +1
Off-policy Evaluation (OPE) methods are crucial tools for evaluating policies in high-stakes domains such as healthcare, where direct deployment is often infeasible, unethical, or…
Generalizing Off-Policy Evaluation From a Causal Perspective For Sequential Decision-Making
Sonali Parbhoo, Shalmali Joshi, Finale Doshi-Velez
Assessing the effects of a policy based on observational data from a different policy is a common problem across several high-stake decision-making domains, and several off-policy…
Learning-to-defer for sequential medical decision-making under uncertainty
Shalmali Joshi, Sonali Parbhoo, Finale Doshi-Velez
Learning-to-defer is a framework to automatically defer decision-making to a human expert when ML-based decisions are deemed unreliable. Existing learning-to-defer frameworks are n…
Pulling Up by the Causal Bootstraps: Causal Data Augmentation for Pre-training Debiasing
Sindhu C. M. Gowda, Shalmali Joshi, Haoran Zhang +1
Machine learning models achieve state-of-the-art performance on many supervised learning tasks. However, prior evidence suggests that these models may learn to rely on shortcut bia…
Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysis
Martin Pawelczyk, Chirag Agarwal, Shalmali Joshi +2
As machine learning (ML) models become more widely deployed in high-stakes applications, counterfactual explanations have emerged as key tools for providing actionable model explan…
An Empirical Framework for Domain Generalization in Clinical Settings
Haoran Zhang, Natalie Dullerud, Laleh Seyyed-Kalantari +3
Clinical machine learning models experience significantly degraded performance in datasets not seen during training, e.g., new hospitals or populations. Recent developments in doma…
Learning Under Adversarial and Interventional Shifts
Harvineet Singh, Shalmali Joshi, Finale Doshi-Velez +1
Machine learning models are often trained on data from one distribution and deployed on others. So it becomes important to design models that are robust to distribution shifts. Mos…
Towards Robust and Reliable Algorithmic Recourse
Sohini Upadhyay, Shalmali Joshi, Himabindu Lakkaraju
As predictive models are increasingly being deployed in high-stakes decision making (e.g., loan approvals), there has been growing interest in post hoc techniques which provide rec…
Confounding Feature Acquisition for Causal Effect Estimation
Shirly Wang, Seung Eun Yi, Shalmali Joshi +1
Reliable treatment effect estimation from observational data depends on the availability of all confounding information. While much work has targeted treatment effect estimation fr…
Ethical Machine Learning in Health Care
Irene Y. Chen, Emma Pierson, Sherri Rose +3
The use of machine learning (ML) in health care raises numerous ethical concerns, especially as models can amplify existing health inequities. Here, we outline ethical consideratio…
Probabilistic Machine Learning for Healthcare
Irene Y. Chen, Shalmali Joshi, Marzyeh Ghassemi +1
Machine learning can be used to make sense of healthcare data. Probabilistic machine learning models help provide a complete picture of observed data in healthcare. In this review,…
Sequential Explanations with Mental Model-Based Policies
Arnold YS Yeung, Shalmali Joshi, Joseph Jay Williams +1
The act of explaining across two parties is a feedback loop, where one provides information on what needs to be explained and the other provides an explanation relevant to this inf…
Counterfactually Guided Off-policy Transfer in Clinical Settings
Taylor W. Killian, Marzyeh Ghassemi, Shalmali Joshi
Domain shift, encountered when using a trained model for a new patient population, creates significant challenges for sequential decision making in healthcare since the target doma…
What went wrong and when? Instance-wise Feature Importance for Time-series Models
Sana Tonekaboni, Shalmali Joshi, Kieran Campbell +2
Explanations of time series models are useful for high stakes applications like healthcare but have received little attention in machine learning literature. We propose FIT, a fram…
Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
Shalmali Joshi, Oluwasanmi Koyejo, Warut Vijitbenjaronk +2
Machine learning based decision making systems are increasingly affecting humans. An individual can suffer an undesirable outcome under such decision making systems (e.g. denied cr…
What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use
Sana Tonekaboni, Shalmali Joshi, Melissa D McCradden +1
Translating machine learning (ML) models effectively to clinical practice requires establishing clinicians' trust. Explainability, or the ability of an ML model to justify its outc…
xGEMs: Generating Examplars to Explain Black-Box Models
Shalmali Joshi, Oluwasanmi Koyejo, Been Kim +1
This work proposes xGEMs or manifold guided exemplars, a framework to understand black-box classifier behavior by exploring the landscape of the underlying data manifold as data po…
Identifiable Phenotyping using Constrained Non-Negative Matrix Factorization
Shalmali Joshi, Suriya Gunasekar, David Sontag +1
This work proposes a new algorithm for automated and simultaneous phenotyping of multiple co-occurring medical conditions, also referred as comorbidities, using clinical notes from…