Search Results for author:
Found 22 papers, 5 papers with code
Machine Learning for Health symposium 2022 -- Extended Abstract track
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, 2022, in New Orleans, Louisiana, USA.
"Why did the Model Fail?": Attributing Model Performance Changes to Distribution Shifts
In this work, we introduce the problem of attributing performance differences between environments to distribution shifts in the underlying data generating mechanisms.
Towards Robust Off-Policy Evaluation via Human Inputs
When deployment environments are expected to undergo changes (that is, dataset shifts), it is important for OPE methods to perform robust evaluation of the policies amidst such changes.
Generalizing Off-Policy Evaluation From a Causal Perspective For Sequential Decision-Making
A precise description of the causal estimand highlights which OPE estimands are identifiable from observational data under the stated generative assumptions.
Learning-to-defer for sequential medical decision-making under uncertainty
Our deferral policy is adaptive to the non-stationarity in the dynamics.
Pulling Up by the Causal Bootstraps: Causal Data Augmentation for Pre-training Debiasing
This systematic investigation underlines the importance of accounting for the underlying data-generating mechanisms and fortifying data-preprocessing pipelines with a causal framework to develop methods robust to confounding biases.
Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysis
As machine learning (ML) models become more widely deployed in high-stakes applications, counterfactual explanations have emerged as key tools for providing actionable model explanations in practice.
Learning Under Adversarial and Interventional Shifts
Most of the existing work focuses on optimizing for either adversarial shifts or interventional shifts.
An Empirical Framework for Domain Generalization in Clinical Settings
In this work, we benchmark the performance of eight domain generalization methods on multi-site clinical time series and medical imaging data.
Towards Robust and Reliable Algorithmic Recourse
To address this problem, we propose a novel framework, RObust Algorithmic Recourse (ROAR), that leverages adversarial training for finding recourses that are robust to model shifts.
What went wrong and when?\\ Instance-wise feature importance for time-series black-box models
Explanations of time series models are useful for high stakes applications like healthcare but have received little attention in machine learning literature.
Confounding Feature Acquisition for Causal Effect Estimation
Reliable treatment effect estimation from observational data depends on the availability of all confounding information.
Probabilistic Machine Learning for Healthcare
Machine learning can be used to make sense of healthcare data.
Ethical Machine Learning in Health Care
The use of machine learning (ML) in health care raises numerous ethical concerns, especially as models can amplify existing health inequities.
Sequential Explanations with Mental Model-Based Policies
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 information.
Counterfactually Guided Off-policy Transfer in Clinical Settings
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 domain may be both data-scarce and confounded.
What went wrong and when? Instance-wise Feature Importance for Time-series Models
Explanations of time series models are useful for high stakes applications like healthcare but have received little attention in machine learning literature.
Explaining Time Series by Counterfactuals
We propose a method to automatically compute the importance of features at every observation in time series, by simulating counterfactual trajectories given previous observations.
Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
We then provide a mechanism to generate the smallest set of changes that will improve an individual's outcome.
What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use
Translating machine learning (ML) models effectively to clinical practice requires establishing clinicians' trust.
xGEMs: Generating Examplars to Explain Black-Box Models
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 points cross decision boundaries.
Identifiable Phenotyping using Constrained Non-Negative Matrix Factorization
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 the electronic health records (EHRs).
