# Convergence Analysis of Two-Layer Neural Networks under Gaussian Input Masking

arXiv: https://arxiv.org/abs/2602.17423 · HTML: https://mlsanity.com/paper/2602.17423/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2026.

## Abstract (arXiv)

We investigate the convergence guarantee of two-layer neural network training with Gaussian randomly masked inputs. This scenario corresponds to Gaussian dropout at the input level, or noisy input training common in sensor networks, privacy-preserving training, and federated learning, where each user may have access to partial or corrupted features. Using a Neural Tangent Kernel (NTK) analysis, we demonstrate that training a two-layer ReLU network with Gaussian randomly masked inputs achieves linear convergence up to an error region proportional to the mask's variance. A key technical contribution is resolving the randomness within the non-linear activation, a problem of independent interest.