Add to ORKGSpurious correlations allow flexible models to predict well during training but poorly on related test distributions. Recent work has shown that models that satisfy particular independencies involving correlation-inducing \textit{nuisance} variables have guarantees on their test performance. Enforcing such independencies requires nuisances to be observed during training. However, nuisances, such as demographics or image background labels, are often missing. Enforcing independence on just the observed data does not imply independence on the entire population. Here we derive \acrshort{mmd} estimators used for invariance objectives under missing nuisances. On simulations and clinical data, optimizing through these estimates achieves test perfo...
As statistical classifiers become integrated into real-world applications, it is important to consid...
Thesis (Ph.D.)--University of Washington, 2020Modern machine learning algorithms have been able to a...
In machine learning, we traditionally evaluate the performance of a single model, averaged over a co...
In many prediction problems, spurious correlations are induced by a changing relationship between th...
In many application areas, predictive models are used to support or make important decisions. There ...
Spurious correlations in training data often lead to robustness issues since models learn to use the...
Due to spurious correlations, machine learning systems often fail to generalize to environments whos...
In many application areas, predictive models are used to support or make important decisions. There ...
A trained neural network can be interpreted as a structural causal model (SCM) that provides the eff...
Recent interest in the external validity of prediction models (i.e., the problem of different train ...
We propose to learn invariant representations, in the data domain, to achieve interpretability in al...
Machine learning algorithms typically assume that training and test examples are drawn from the same...
The popularity of machine learning in both academia and industry has experienced unparalleled growth...
There exist features that are related to the label in the same way across different settings for tha...
When deployed in the real world, machine learning models inevitably encounter changes in the data di...
As statistical classifiers become integrated into real-world applications, it is important to consid...
Thesis (Ph.D.)--University of Washington, 2020Modern machine learning algorithms have been able to a...
In machine learning, we traditionally evaluate the performance of a single model, averaged over a co...
In many prediction problems, spurious correlations are induced by a changing relationship between th...
In many application areas, predictive models are used to support or make important decisions. There ...
Spurious correlations in training data often lead to robustness issues since models learn to use the...
Due to spurious correlations, machine learning systems often fail to generalize to environments whos...
In many application areas, predictive models are used to support or make important decisions. There ...
A trained neural network can be interpreted as a structural causal model (SCM) that provides the eff...
Recent interest in the external validity of prediction models (i.e., the problem of different train ...
We propose to learn invariant representations, in the data domain, to achieve interpretability in al...
Machine learning algorithms typically assume that training and test examples are drawn from the same...
The popularity of machine learning in both academia and industry has experienced unparalleled growth...
There exist features that are related to the label in the same way across different settings for tha...
When deployed in the real world, machine learning models inevitably encounter changes in the data di...
As statistical classifiers become integrated into real-world applications, it is important to consid...
Thesis (Ph.D.)--University of Washington, 2020Modern machine learning algorithms have been able to a...
In machine learning, we traditionally evaluate the performance of a single model, averaged over a co...