Ensuring that large language models (LMs) are fair, robust and useful
re...
Learned classifiers should often possess certain invariance properties m...
An important component in deploying machine learning (ML) in safety-crit...
Supervised learning typically relies on manual annotation of the true la...
ML-based predictions are used to inform consequential decisions about
in...
There are growing concerns that algorithms, which increasingly make or
i...
Saliency methods are a popular approach for model debugging and
explaina...
In many machine learning settings there is an inherent tension between
f...
An agnostic PAC learning algorithm finds a predictor that is competitive...
Prediction algorithms assign numbers to individuals that are popularly
u...
A fancy learning algorithm A outperforms a baseline method B when they
a...
As algorithms are increasingly used to make important decisions pertaini...
We study fairness in machine learning. A learning algorithm, given a tra...