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

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. We prove that even under these strong simplifying assumptions, while GD successfully converges to an optimal robustness margin, effectively maximizing the distance between the decision boundary and the training points, this convergence occurs at a prohibitively slow rate, scaling strictly as Theta(1/ln(t)). To the best of our knowledge, this establishes the first explicit lower bound on the convergence rate of the robustness margin in a non-linear model. Through empirical simulations, we further demonstrate that this inherent failure mode is pervasive, exhibiting the exact same tight convergence rate across multiple natural network initializations. Our theoretical guarantees are derived via a rigorous analysis of the GD trajectories across the distinct activation patterns of the model. Specifically, we develop tight control over the system's dynamics to bound the trajectory of the decision boundary, overcoming the primary technical challenge introduced by the non-linear nature of the architecture.

Related

• Gradient descent at the Edge of Stability: free energy model and kinetic description of the two-layer network
• Spectral Dynamics in Deep Networks: Feature Learning, Outlier Escape, and Learning Rate Transfer
• Gradient Descent as a Perceptron Algorithm: Understanding Dynamics and Implicit Acceleration

Source: arXiv cs.AI | 2026-10-12