The edge-of-chaos condition preserves first-order input perturbations in wide randomly initialized networks, but physics-informed losses, score matching and derivative regularization depend on higher...
arXiv:2608. 08350v1 Announce Type: new Abstract: The initialisation of deep neural networks determines whether information and gradients can propagate across depth, yet a unified theory connecting these properties to learning dynamics remains elusive.
arXiv:2506. 08764v3 Announce Type: replace Abstract: Deep neural networks are known to suffer from exploding or vanishing gradients as depth increases, a phenomenon closely tied to the spectral behavior of the input-output Jacobian.
arXiv:2608. 14638v1 Announce Type: new Abstract: In this paper we study autoencoders, a special class of deep neural nets (DNNs) whose performance can be characterized via their fixed points.
arXiv:2602. 05779v2 Announce Type: replace Abstract: The Edge-of-Chaos (EoC) theory developed for the random initialization of deep networks allows more efficient training by both preserving information in the initial outputs of the network and minimising exploding or vanishing gradients through characterisation of the intermediate layers as Gaussian processes.
The paper investigates how deep residual networks behave when their initial weights are correlated across layers. It confirms a conjecture that such correlated initializations interpolate between a Brownian stochastic differential equation (for independent weights) and an ordinary differential equation (for perfectly correlated weights). By applying a feature function to a stationary Gaussian sequence with regularly varying correlation, the authors prove that a unique critical scaling exists, leading the infinite‑depth limit to a Young differential equation driven by a Hermite process, which reduces to fractional Brownian motion when the feature function has Hermite rank one. The study shows that the correlation structure and Hermite rank of the initialization uniquely determine the critical scaling and asymptotic limit, making them meaningful hyperparameters in the asymptotic regime, whereas finite‑variance i.i.d. initialization always yields a Brownian driver regardless of distribution.
arXiv:2502. 11152v4 Announce Type: replace-cross Abstract: The optimization foundations of deep linear networks have recently received significant attention.
arXiv:2210. 16286v2 Announce Type: replace Abstract: To understand the training dynamics of neural networks, prior studies have considered the mean-field limit of two-layer neural networks as the width tends to infinity, establishing theoretical guarantees for its convergence under gradient flow training as well as approximation and generalization capabilities.
arXiv:2401. 04013v2 Announce Type: replace Abstract: Deep learning models, such as wide neural networks, can be conceptualized as nonlinear dynamical physical systems characterized by a multitude of interacting degrees of freedom.
The paper investigates gradient descent dynamics in the Edge of Stability regime, where a large learning rate causes persistent oscillations linked to improved generalization. It introduces a tractable continuous‑time mean–fluctuation model that couples the window‑averaged trajectory with its fluctuation covariance, derives this model rigorously from a sharp‑valley framework, and analyzes its stationary states and linear stability. The authors also extend the model to wide two‑layer networks, deriving a Wasserstein‑2 gradient flow for weights and fluctuations, proving well‑posedness, a mean‑field limit, and conditional convergence results, with numerical experiments illustrating the predictions and finite‑time limitations.
arXiv:2607. 12332v1 Announce Type: new Abstract: We study the gradient flow dynamics of diagonal linear networks for regression tasks under infinitesimal initialization.
arXiv:2311. 15365v3 Announce Type: replace Abstract: We study an idealized training process for deep neural networks in a continuous-depth, mean-field model in which each layer is parameterized by a probability measure on a Euclidean parameter space.