Provable FDR Control for Deep Feature Selection: Deep MLPs and Beyond

Excerpt

arXiv:2512.04696v3 Announce Type: replace-cross Abstract: We develop a flexible feature selection framework based on deep neural networks that approximately controls the false discovery rate (FDR), a measure of Type-I error. The method applies to architectures whose first layer is fully connected. From the second layer onward, it accommodates multilayer perceptrons (MLPs) of arbitrary width and depth, convolutional and recurrent networks, attention mechanisms, residual connections, and dropout.