Michaela Hardt
YOU?
Author Swipe
Toward Falsifying Causal Graphs Using a Permutation-Based Test Open
Understanding causal relationships among the variables of a system is paramount to explain and control its behavior. For many real-world systems, however, the true causal graph is not readily available and one must resort to predictions ma…
The PetShop Dataset -- Finding Causes of Performance Issues across Microservices Open
Identifying root causes for unexpected or undesirable behavior in complex systems is a prevalent challenge. This issue becomes especially crucial in modern cloud applications that employ numerous microservices. Although the machine learnin…
Toward Falsifying Causal Graphs Using a Permutation-Based Test Open
Understanding causal relationships among the variables of a system is paramount to explain and control its behavior. For many real-world systems, however, the true causal graph is not readily available and one must resort to predictions ma…
View article: Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud
Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud Open
Understanding the predictions made by machine learning (ML) models and their\npotential biases remains a challenging and labor-intensive task that depends on\nthe application, the dataset, and the specific model. We present Amazon\nSageMak…
It is Time for Bioethicists to Enter the Arena of Machine Learning Ethics Open
This article refers to:Identifying Ethical Considerations for Machine Learning Healthcare Applications
Explaining an increase in predicted risk for clinical alerts Open
Much work aims to explain a model's prediction on a static input. We consider explanations in a temporal setting where a stateful dynamical model produces a sequence of risk estimates given an input at each time step. When the estimated ri…
View article: Linear Dynamics: Clustering without identification
Linear Dynamics: Clustering without identification Open
Linear dynamical systems are a fundamental and powerful parametric model class. However, identifying the parameters of a linear dynamical system is a venerable task, permitting provably efficient solutions only in special cases. This work …
Ensuring Fairness in Machine Learning to Advance Health Equity Open
Machine learning is used increasingly in clinical care to improve diagnosis, treatment selection, and health system efficiency. Because machine-learning models learn from historically collected data, populations that have experienced human…