Neural sequence models based on the transformer architecture have demonstrated
remarkable\emph {in-context learning}(ICL) abilities, where they can perform new tasks …

We empirically show that the test error of deep networks can be estimated by simply training
the same architecture on the same training set but with a different run of Stochastic Gradient …

While most machine learning models can provide confidence in their predictions, confidence
is insufficient to understand a prediction's reliability. For instance, the model may have a low …

This work studies the behavior of shallow ReLU networks trained with the logistic loss via
gradient descent on binary classification data where the underlying data distribution is …

Uncertainty quantification is a central challenge in reliable and trustworthy machine
learning. Naive measures such as last-layer scores are well-known to yield overconfident …

The prediction accuracy of machine learning methods is steadily increasing, but the
calibration of their uncertainty predictions poses a significant challenge. Numerous works …

In response to everyday queries, humans explicitly signal uncertainty and offer alternative
answers when they are unsure. Machine learning models that output calibrated prediction …

Deploying task-oriented dialog ToD systems for new domains and tasks requires natural
language understanding models that are 1) resource-efficient and work under low-data …

In this paper, we consider a wireless federated inference scenario in which devices and a
server share a pre-trained machine learning model. The devices communicate statistical …

We investigate popular resampling methods for estimating the uncertainty of statistical
models, such as subsampling, bootstrap and the jackknife, and their performance in high …