151 citations · 321 across the 18 of their papers we have counts for
Showing stat.MLShow all
3 papers · 1 filter
stat.ML2026
Optimal approximation of smooth functions by ReLU neural networks
Thomas Nagler
We study uniform approximation of the Hölder ball by fully connected ReLU networks. Except in the one-dimensional Lipschitz case, existing constructions r…
stat.ML2023★ 2 cited
Statistical Foundations of Prior-Data Fitted Networks
Thomas Nagler
Prior-data fitted networks (PFNs) were recently proposed as a new paradigm for machine learning. Instead of training the network to an observed training set, a fixed model is pre-t…
stat.ML2023★ 1 cited
Approximately Bayes-Optimal Pseudo Label Selection
Julian Rodemann, Jann Goschenhofer, Emilio Dorigatti +2
Semi-supervised learning by self-training heavily relies on pseudo-label selection (PLS). The selection often depends on the initial model fit on labeled data. Early overfitting mi…