The paper investigates how Adam’s update rule relates to natural gradient descent (NGD) by treating Adam as a diagonal empirical Fisher approximation with additional factors such as diagonal truncation, empirical label substitution, and temporal lag. Using a scale‑invariant metric, the authors quantify Adam’s geometric deviation from true NGD across four loss landscapes—well‑conditioned and ill‑conditioned linear regression, logistic regression, and a small neural network—finding that deviation is low in well‑conditioned settings but can reach about 10³ in ill‑conditioned or non‑convex scenarios. Despite higher geometric drift correlating with slower early optimization, Adam still achieves low final loss, and the improved empirical Fisher (iEF) yields more stable trajectories than the standard empirical Fisher (EF).
arXiv:2605. 29547v2 Announce Type: replace-cross Abstract: Deep learning optimization relies heavily on the assumption of smooth loss landscapes, a condition systematically violated by modern architectures due to non-smooth components such as ReLU activations and quantization operators.
arXiv:2608. 16760v1 Announce Type: new Abstract: Reliable optimization is central to neural network (NN) training, yet Adam, the default optimizer for modern LLMs, rests on a fragile foundation.
The paper investigates why setting the two momentum parameters of Adam equal (β1=β2) has a special dynamic effect. By analysing Adam in continuous time, the authors show that the update decomposes into a sign component, a magnitude‑lag term proportional to the difference between the two memory times, and other terms. This lag term disappears exactly when β1=β2, making the diagonal the only regime where the mismatch‑induced response is structurally absent. Experiments on six vision and language tasks confirm that tied configurations are sign‑dominated, have smaller lag contributions, and exhibit smoother update‑norm trajectories.
The paper studies how Adam’s two momentum timescales, β1 and β3, influence loss spikes during neural‑network training. By mapping training dynamics across the (β1,β3) plane, the authors find an approximately linear boundary, 1-β3 = C(1-β1), that separates spiky from non‑spiky behavior, with the coefficient C linked to the effective loss exponent in superquadratic loss functions. They also show that confident cross‑entropy losses create a core–wall landscape that behaves superquadratically at the scale of an optimizer update, explaining the observed spikes.
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.
arXiv:2607. 09967v1 Announce Type: cross Abstract: Many neural networks operations have a multiplicative nature rather than additive: halving or doubling a norm are analogous relatively but require unequal optimization distances when taking linear steps.
arXiv:2607. 27383v1 Announce Type: new Abstract: We establish the first convergence guarantees for the plain vector-form \emph{Adam} optimizer under heavy-tailed stochastic noise.
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:2602. 10204v2 Announce Type: replace Abstract: We introduce MVN-Grad (Momentum on Variance-Normalized Gradients), an Adam-style optimizer that improves stability and performance by combining two complementary ideas: variance-based normalization and momentum applied after normalization.
arXiv:2608.20638v2 Announce Type: replace-cross Abstract: The edge-of-stability (EoS) phenomenon of full-batch Adam has been widely observed, yet its underlying dynamical mechanism remains poorly und...
arXiv:2607. 03998v1 Announce Type: new Abstract: The local sharpness of the loss, the top Hessian eigenvalue $\lambda_1$, determines the largest stable gradient step, but measuring it normally requires Lanczos or Hessian-vector iterations.
arXiv:2511. 13465v5 Announce Type: replace Abstract: This paper studies the exponential decay mechanism of the second-moment estimate in Adam.