The performance of computer vision models significantly improves with more labeled data.
However, the acquisition of labeled data is limited by the high cost. To mitigate the reliance …

Active learning theories and methods have been extensively studied in classical statistical
learning settings. However, deep active learning, ie, active learning with deep learning …

Textbook wisdom advocates for smooth function fits and implies that interpolation of noisy
data should lead to poor generalization. A related heuristic is that fitting parameters should …

Previously, statistical textbook wisdom has held that interpolating noisy data will generalize
poorly, but recent work has shown that data interpolation schemes can generalize well. This …

In this work we discuss the problem of active learning. We present an approach that is based
on A-optimal experimental design of ill-posed problems and show how one can optimally …

Deep learning has yielded extraordinary results in vision and natural language processing,
but this achievement comes at a cost. Most deep learning models require enormous …

Contemporary Artificial Intelligence (AI) stands on two legs: large training data corpora and
many-parameter artificial neural networks (ANNs). The data corpora are needed to …

Textbook wisdom advocates for smooth function fits and implies that interpolation of noisy
data should lead to poor generalization. A related heuristic is that fitting parameters should …

Node classification in attributed graphs is an important task in multiple practical settings, but
it can often be difficult or expensive to obtain labels. Active learning is an approach that aims …

Overparameterized machine learning models are often fit perfectly to training data, yet
remarkably generalize well to new data. However, learning good models can require an …