3 papers
cs.LG2025
Active Learning with Neural Networks: Insights from Nonparametric Statistics
Yinglun Zhu, Robert Nowak
Deep neural networks have great representation power, but typically require large numbers of training examples. This motivates deep active learning methods that can significantly r…
stat.ML2025
Efficient Active Learning with Abstention
Yinglun Zhu, Robert Nowak
The goal of active learning is to achieve the same accuracy achievable by passive learning, while using much fewer labels. Exponential savings in terms of label complexity have bee…
stat.ML2024
Weighted variation spaces and approximation by shallow ReLU networks
Ronald DeVore, Robert D. Nowak, Rahul Parhi +1
We investigate the approximation of functions on a bounded domain by the outputs of single-hidden-layer ReLU neural networks of width . This form of…