Research

On the Rate of Convergence of GD in Non-linear Neural Networks: An Adversarial Robustness Perspective

Single source1 source12 Oct 2026

arXiv:2603.02095v2 Announce Type: replace-cross Abstract: We study the convergence dynamics of Gradient Descent (GD) in a minimal binary classification setting, consisting of a two-neuron ReLU network and two training instances.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2603.02095

← Back to all developments · Signals are a development reported by more than one source. See the methodology.