paper-with-me

Papers

From Adam to Adam-Like Lagrangians: Second-Order Nonlocal Dynamics

2026-02-09 · Carlos Heredia arxiv

In this paper, we derive an accelerated continuous-time formulation of Adam by modeling it as a second-order integro-differential dynamical system. We relate this inertial nonlocal model to an existing first-order nonlocal Adam flow through an $α$-refinement limit, and we provide Lyapunov-based stability and convergence analyses. We also introduce an Adam-inspired nonlocal Lagrangian formulation, offering a variational viewpoint. Numerical simulations on Rosenbrock-type examples show agreement between the proposed dynamics and discrete Adam.

📄 PDF Abstract BibTeX arXiv:2602.09101

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AdamNX: An Adam improvement algorithm based on a novel exponential decay mechanism for the second-order moment estimate

2025-11-17 · Meng Zhu, Quan Xiao, Weidong Min arxiv

Since the 21st century, artificial intelligence has been leading a new round of industrial revolution. Under the training framework, the optimization algorithm aims to stably converge high-dimensional optimization to loc…

Studying K-FAC Heuristics by Viewing Adam through a Second-Order Lens

2023-10-23 · Ross M. Clarke, José Miguel Hernández-Lobato

Research into optimisation for deep learning is characterised by a tension between the computational efficiency of first-order, gradient-based methods (such as SGD and Adam) and the theoretical efficiency of second-order…

Computational EfficiencySecond-order methods

Conjugate-Gradient-like Based Adaptive Moment Estimation Optimization Algorithm for Deep Learning

2024-04-02 · Jiawu Tian, Liwei Xu, Xiaowei Zhang, Yongqi Li

Training deep neural networks is a challenging task. In order to speed up training and enhance the performance of deep neural networks, we rectify the vanilla conjugate gradient as conjugate-gradient-like and incorporate…

UAdam: Unified Adam-Type Algorithmic Framework for Non-Convex Stochastic Optimization

2023-05-09 · Yiming Jiang, Jinlan Liu, Dongpo Xu, Danilo P. Mandic

Adam-type algorithms have become a preferred choice for optimisation in the deep learning setting, however, despite success, their convergence is still not well understood. To this end, we introduce a unified framework f…

Stochastic OptimizationVocal Bursts Type Prediction

Adaptive Moment Estimation Optimization Algorithm Using Projection Gradient for Deep Learning

2025-03-13 · Yongqi Li, Xiaowei Zhang

Training deep neural networks is challenging. To accelerate training and enhance performance, we propose PadamP, a novel optimization algorithm. PadamP is derived by applying the adaptive estimation of the p-th power of …