Mildly Overparametrized Neural Nets can Memorize Training Data Efficiently

26 September 2019

Papers citing "Mildly Overparametrized Neural Nets can Memorize Training Data Efficiently"

5 / 5 papers shown

Title
$\emph{Lifted} RDT based capacity analysis of the 1-hidden layer treelike \emph{sign} perceptrons neural networks$ \emph{Lifted} RDT based capacity analysis of the 1-hidden layer treelike \emph{sign} perceptrons neural networks M. Stojnic 20 1 0 13 Dec 2023
Capacity of the treelike sign perceptrons neural networks with one hidden layer -- RDT based upper bounds M. Stojnic 16 4 0 13 Dec 2023
Learning Parities with Neural Networks Amit Daniely Eran Malach 13 76 0 18 Feb 2020
Memory capacity of neural networks with threshold and ReLU activations Roman Vershynin 13 21 0 20 Jan 2020
Active Subspace of Neural Networks: Structural Analysis and Universal Attacks Chunfeng Cui Kaiqi Zhang Talgat Daulbaev Julia Gusak Ivan V. Oseledets Zheng-Wei Zhang AAML 22 25 0 29 Oct 2019