.png){kind=icon}
返回
A stochastic recursive gradient algorithm with inertial extrapolation for non-convex problems and machine learning
.png){kind=icon}
OA
AI
DOI：10.1007/s13042-024-02524-6.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In recent years, the inertial extrapolation step has gained significant attention due to its capacity to expedite algorithm convergence. This technology has found widespread application across various algorithms. However, within the domain of machine learning, the utilization of extrapolation technology has yielded limited results. Therefore, we apply it to stochastic optimization algorithms to address non-convex and machine learning problems. By integrating the inertial extrapolation step and the modified Barzilai-Borwein (BB) technique into the SARAH framework, we propose an inertial stochastic recurrence gradient method. This method incorporates both the inertial extrapolation step and the improved BB technique. Through theoretical analysis presented in this paper, we demonstrate that the algorithm converges to a global optimum and analyze the linear convergence rate of the non-convex ((lambda) over tilde -gradient-dominated) objective functions. The numerical results obtained from evaluating three widely utilized machine learning problems clearly illustrate the superior performance and practical feasibility of the proposed algorithm.
Keyword:
Extrapolation
Algorithm
Non-convex
Global optimum
Convergence
Numerical results
期刊
IF:
2.7
论文数:
3.2K
被引数:
5.6K
机构
引用论文
分享收藏Structural interpretation of lineaments using satellite image processing: A case study in the vicinity of the Charvak reservoir利用卫星图像处理对线性构造进行结构解释：查尔瓦克水库周边的案例研究OAAI
OAAI分享收藏Performance Evaluation of a Feature-Importance-based Feature Selection Method for Time Series Prediction基于特征重要性特征选择方法的时间序列预测性能评估OAAI
OAAI分享收藏分享收藏Accommodating Stealth Assessment in Serious Games: Towards Developing a Generic Tool.png)
2018 10th International Conference on Virtual Worlds and Games for Serious Applications (VS-Games)
OAAI
2018 10th International Conference on Virtual Worlds and Games for Serious Applications (VS-Games)IF0
OAAI分享收藏
查看更多内容