paper-with-me

홈 › Papers

EXAdam: The Power of Adaptive Cross-Moments

2024-12-29 · Ahmed M. Adly

This paper introduces EXAdam ($\textbf{EX}$tended $\textbf{Adam}$), a novel optimization algorithm that builds upon the widely-used Adam optimizer. EXAdam incorporates two key enhancements: (1) new debiasing terms for improved moment estimation and (2) a gradient-based acceleration mechanism for increased responsiveness to the current loss landscape. These innovations work synergistically to address limitations of the original Adam algorithm, potentially offering improved convergence properties, enhanced ability to escape saddle points, and potentially greater robustness to hyperparameter choices, though this requires further investigation. We provide a theoretical analysis of EXAdam's components and their interactions, highlighting the algorithm's potential advantages in navigating complex optimization landscapes. Empirical evaluations demonstrate EXAdam's superiority over Adam, achieving 38.46% faster convergence and yielding improvements of 1.96%, 2.17%, and 1.17% in training, validation, and testing accuracies, respectively, when applied to a CNN trained on the CIFAR-10 dataset. While these results are promising, further empirical validation across diverse tasks is essential to fully gauge EXAdam's efficacy. Nevertheless, EXAdam represents a significant advancement in adaptive optimization techniques, with promising implications for a wide range of machine learning applications. This work aims to contribute to the ongoing development of more efficient, adaptive, and universally applicable optimization methods in the field of machine learning and artificial intelligence.

📄 PDF Abstract BibTeX arXiv:2412.20302

Code (1)

AhmedMostafa16/EXAdam 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Adam 설명 없음

Similar Papers 제목 키워드 기반

Adaptive Student's t-distribution with method of moments moving estimator for nonstationary time series

2023-04-06 · Jarek Duda

The real life time series are usually nonstationary, bringing a difficult question of model adaptation. Classical approaches like ARMA-ARCH assume arbitrary type of dependence. To avoid their bias, we will focus on recen…

PhilosophyTime Series

Implicitly Adaptive Importance Sampling

2019-06-20 · Topi Paananen, Juho Piironen, Paul-Christian Bürkner, Aki Vehtari

Adaptive importance sampling is a class of techniques for finding good proposal distributions for importance sampling. Often the proposal distributions are standard probability distributions whose parameters are adapted …

Acutum: When Generalization Meets Adaptability

2019-09-25 · Xunpeng Huang, Zhengyang Liu, Zhe Wang, Yue Yu 외

In spite of the slow convergence, stochastic gradient descent (SGD) is still the most practical optimization method due to its outstanding generalization ability and simplicity. On the other hand, adaptive methods have a…

BIG-bench Machine Learning

ACMo: Angle-Calibrated Moment Methods for Stochastic Optimization

2020-06-12 · Xunpeng Huang, Runxin Xu, Hao Zhou, Zhe Wang 외

Due to its simplicity and outstanding ability to generalize, stochastic gradient descent (SGD) is still the most widely used optimization method despite its slow convergence. Meanwhile, adaptive methods have attracted ri…

BIG-bench Machine LearningStochastic Optimization

AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models

2026-02-06 · Yuming Li, Qingyu Li, Chengyu Bai, Xiangyang Luo 외 arxiv

Reinforcement learning from human feedback (RLHF) shows promise for aligning diffusion and flow models, yet policy optimization methods such as GRPO suffer from inefficient and static sampling strategies. These methods t…

Text-to-Image GenerationReinforcement Learning