The paper introduces the edge coupling, a functional whose critical points correspond to the fixed points and period‑two orbits of gradient descent. It shows that both central flow and rod flow—previous continuous‑time models for the edge of stability—can be derived from this edge coupling, with rod flow coarse‑graining only the fastest time scale and central flow coarse‑graining both fast and intermediate scales. The authors extend these derivations to momentum methods such as heavy ball and Adam, and experimentally confirm that the resulting flows track discrete iterates across all training phases, including the transition to the edge of stability.
arXiv:2606. 18080v1 Announce Type: new Abstract: Gradient descent in deep learning may operate at the edge of stability (EoS), a regime in which the largest eigenvalue of the loss Hessian hovers near the stability threshold $2/\eta$, where $\eta$ is the learning rate.
The paper investigates how continuous symmetries in neural networks, which give rise to conserved quantities under gradient flow, behave when training with finite‑step gradient descent at the edge of stability (EOS). By applying central flow dynamics, the authors show that curvature corrections cause a finite‑dimensional drift driven by oscillation covariance along critical parameter directions. They analyze this effect in a scalar two‑layer model, two‑layer matrix factorisation, and a two‑layer ReLU network, demonstrating which conservation laws persist or break under EOS conditions.
arXiv:2609.01034v1 Announce Type: new Abstract: The central flow of Cohen et al. (2025) is an empirically accurate continuous-time model of gradient descent at the edge of stability in deep learning,...
arXiv:2606. 05326v1 Announce Type: cross Abstract: We study the dynamics of gradient descent in the Edge of Stability regime, where the learning rate is large enough to induce persistent oscillations in the loss and the sharpness.
arXiv:2607. 04993v1 Announce Type: cross Abstract: Many phenomena of deep learning are dynamical: they concern not only which minima exist, but how gradient descent reaches, avoids, or selects among them.
arXiv:2604. 08742v2 Announce Type: replace-cross Abstract: Adam is widely used, but its convergence theory remains incomplete even in the deterministic full-batch setting because momentum and adaptive preconditioning are tightly coupled.
arXiv:2605. 22432v2 Announce Type: replace Abstract: Modern deep learning commonly relies on AdamW with prescribed learning rate schedules, but recent works challenge both components: Schedule-Free optimization removes explicit schedules via iterate averaging, and Muon improves the update geometry by orthogonalizing momentum for matrix parameters.
The paper investigates the training dynamics of flow map models, which convert diffusion trajectories into one‑step samplers for efficient probabilistic generation. It provides a theoretical analysis of the functional gradient flow induced by MeanFlow and Lagrangian losses, proving their convergence to the true flow map and identifying the risk of unbounded updates. The authors show that adaptive normalization and a specific reweighting scheme not only bound updates but also guarantee convergence to a neighborhood of the solution, and they confirm these findings with synthetic experiments and image‑generation benchmarks.
The paper investigates how normalization makes neural networks scale‑invariant, creating a feedback loop between learning‑rate schedules and weight decay that controls the effective step size of the optimizer. It derives an exact discrete‑time law showing that a single scalar quantity captures all schedule and decay effects, with norm growth providing a self‑quenching counter‑force that defines a sharp boundary between contraction‑ and expansion‑dominated regimes. Through exact analysis of a normalized regression model and experiments on MLPs, CNNs, GPT‑2, and various datasets, the authors demonstrate that constant learning rates with weight decay are intrinsically unstable, leading to recurrent dynamics, and that adaptive optimizers exhibit weaker stabilization under normalization. "whyItMatters":"The study provides a precise, actionable rule for controlling training dynamics and schedule design in modern deep learning by isolating a single governing quantity for scale‑invariant optimization."
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:2610.01408v1 Announce Type: new Abstract: Trajectory crossing remains a critical bottleneck in Flow Matching (FM), and previous works typically view these crossings from a theoretical optimizat...
arXiv:2505. 13196v3 Announce Type: replace-cross Abstract: We introduce Velocity-Regularized Adam (VRAdam), a physics-inspired optimizer for training deep neural networks that draws on ideas from quartic terms for kinetic energy with its stabilizing effects on various system dynamics.