paper-with-me

홈 › Papers

The Unified Balance Theory of Second-Moment Exponential Scaling Optimizers in Visual Tasks

2024-05-28 · Gongyue Zhang, Honghai Liu

We have identified a potential method for unifying first-order optimizers through the use of variable Second-Moment Exponential Scaling(SMES). We begin with back propagation, addressing classic phenomena such as gradient vanishing and explosion, as well as issues related to dataset sparsity, and introduce the theory of balance in optimization. Through this theory, we suggest that SGD and adaptive optimizers can be unified under a broader inference, employing variable moving exponential scaling to achieve a balanced approach within a generalized formula for first-order optimizers. We conducted tests on some classic datasets and networks to confirm the impact of different balance coefficients on the overall training process.

📄 PDF Abstract BibTeX arXiv:2405.18498

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Ada2MS: A Hybrid Optimization Algorithm Based on Exponential Mixing of Elementwise and Global Second-Moment Estimates

2026-05-19 · Meng Zhu, Quan Xiao, Weidong Min arxiv

Optimization algorithms are core methods by which machine learning models iteratively minimize loss functions, update parameters, learn from data, and improve performance. Momentum SGD and AdamW represent two important o…

Unified Interactive Multimodal Moment Retrieval via Cascaded Embedding-Reranking and Temporal-Aware Score Fusion

2025-12-15 · Toan Le Ngo Thanh, Phat Ha Huu, Tan Nguyen Dang Duy, Thong Nguyen Le Minh 외 arxiv

The exponential growth of video content has created an urgent need for efficient multimodal moment retrieval systems. However, existing approaches face three critical challenges: (1) fixed-weight fusion strategies fail a…

Moment Retrieval

Regularization Implies balancedness in the deep linear network

2025-11-03 · Kathryn Lindsey, Govind Menon arxiv

We use geometric invariant theory (GIT) to study the deep linear network (DLN). The Kempf-Ness theorem is used to establish that the $L^2$ regularizer is minimized on the balanced manifold. We introduce related balancing…

Rethinking Adam: A Twofold Exponential Moving Average Approach

2021-06-22 · Yizhou Wang, Yue Kang, Can Qin, Huan Wang 외

Adaptive gradient methods, e.g. \textsc{Adam}, have achieved tremendous success in machine learning. Scaling the learning rate element-wisely by a certain form of second moment estimate of gradients, such methods are abl…

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…