Zobrazeno 1 - 10
of 76
pro vyhledávání: '"Joshi, Shalmali"'
Autor:
Parziale, Antonio, Agrawal, Monica, Joshi, Shalmali, Chen, Irene Y., Tang, Shengpu, Oala, Luis, Subbaswamy, Adarsh
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. Machine Learning for Health (ML
Externí odkaz:
http://arxiv.org/abs/2211.15564
Machine learning models frequently experience performance drops under distribution shifts. The underlying cause of such shifts may be multiple simultaneous factors such as changes in data quality, differences in specific covariate distributions, or c
Externí odkaz:
http://arxiv.org/abs/2210.10769
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 expensive. When deployment environments are expected to undergo change
Externí odkaz:
http://arxiv.org/abs/2209.08682
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 evaluation (OPE) techniques have been proposed. However, these methods
Externí odkaz:
http://arxiv.org/abs/2201.08262
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 not designed for sequential settings. That is, they defer at every inst
Externí odkaz:
http://arxiv.org/abs/2109.06312
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 biases or spurious correlations (intuitively, correlations that do not ho
Externí odkaz:
http://arxiv.org/abs/2108.12510
Publikováno v:
International Conference on Artificial Intelligence and Statistics (AISTATS), 28-30 March 2022
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. Despite the growing popularity of counterfactual e
Externí odkaz:
http://arxiv.org/abs/2106.09992
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. Most of the existing work focuses on optimizing for either adversarial sh
Externí odkaz:
http://arxiv.org/abs/2103.15933
Autor:
Zhang, Haoran, Dullerud, Natalie, Seyyed-Kalantari, Laleh, Morris, Quaid, Joshi, Shalmali, Ghassemi, Marzyeh
Clinical machine learning models experience significantly degraded performance in datasets not seen during training, e.g., new hospitals or populations. Recent developments in domain generalization offer a promising solution to this problem by creati
Externí odkaz:
http://arxiv.org/abs/2103.11163
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 recourse to affected individuals. These techniques generate recourses und
Externí odkaz:
http://arxiv.org/abs/2102.13620