Adaptive energy-based gradient methods for large-scale optimization and data-driven discovery of dynamical systems via neural networks

人工神经网络 计算机科学 动力系统理论 人工智能 最优控制 深度学习 机器学习 趋同(经济学) 随机优化 理论(学习稳定性) 水准点(测量) 数学优化 数学 物理 量子力学 大地测量学 地理 经济 经济增长
作者
Xuping Tian
标识
DOI:10.31274/td-20240617-16
摘要

Machine learning and data science have revolutionized numerous scientific and engineering domains, promising a renaissance in complex data analysis and understanding. This thesis addresses two critical challenges at the forefront of these fields: (1) developing efficient optimization methods for training large-scale machine learning models, and (2) the discovery of dynamical systems from observational data. To tackle the first challenge, we introduce a new family of gradient-based optimization methods. These methods employ an adaptive energy-based strategy, ensuring unconditional energy stability regardless of the step size (learning rate) value. We provide convergence analyses for both deterministic and stochastic settings, with particular emphasis placed on the SGEM (Stochastic Gradient with Energy and Momentum) method, notable for its incorporation of momentum acceleration. Experimental results on benchmark deep learning problems demonstrate SGEM's rapid convergence and superior generalization capabilities. Furthermore, we investigate the dynamic behavior of a deterministic variant of SGEM through the lens of limiting Ordinary Differential Equations (ODEs). Our results illuminate the impact of momentum and step size on the stability and convergence of discrete schemes. Addressing the second challenge, we propose a data-driven optimal control approach for learning system parameters. This approach is subsequently extended to encompass the learning of the entire governing function by incorporating neural network approximation into the framework. Specifically, we exemplify the data-driven optimal control approach by learning the parameters of the Susceptible-Exposed-Infectious-Recovered (SEIR) model from reported COVID-19 data. The Optimal Control Neural Networks (OCN) framework is demonstrated through its application to a gradient flow system. The training process of the neural networks is meticulously designed using the adjoint method alongside symplectic ODE solvers. Numerical experiments on several canonical systems validate the OCN framework. In summary, this research contributes to the advancement of both the theoretical understanding and practical applications of large-scale optimization in machine learning, as well as the data-driven discovery of dynamical systems.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
薄年完成签到,获得积分10
1秒前
付小源完成签到,获得积分10
2秒前
票子完成签到,获得积分10
2秒前
酷炫迎波完成签到,获得积分10
4秒前
沐晨浠完成签到,获得积分10
4秒前
tcf完成签到,获得积分10
5秒前
MrSong完成签到,获得积分10
6秒前
豆浆来点蒜泥完成签到,获得积分0
7秒前
9秒前
10秒前
可燃冰完成签到,获得积分10
11秒前
11秒前
黄石完成签到,获得积分10
11秒前
Justtry完成签到,获得积分10
11秒前
Sunshine完成签到 ,获得积分10
12秒前
虚心的仙人掌完成签到,获得积分0
13秒前
信远征完成签到,获得积分10
13秒前
落尘完成签到,获得积分10
14秒前
务实小鸽子完成签到 ,获得积分10
15秒前
15秒前
王小磊发布了新的文献求助10
15秒前
Iwan完成签到,获得积分10
15秒前
小蘑菇应助LIUYONG采纳,获得10
19秒前
大气的山彤完成签到,获得积分10
20秒前
苏木发布了新的文献求助10
20秒前
Yep0672完成签到,获得积分10
20秒前
小王发布了新的文献求助10
21秒前
21秒前
22秒前
22秒前
22秒前
粥粥完成签到,获得积分10
23秒前
24秒前
小宋完成签到,获得积分10
24秒前
干净的芮完成签到,获得积分10
24秒前
peace完成签到,获得积分10
24秒前
明天会更美好完成签到,获得积分10
26秒前
初七完成签到,获得积分20
26秒前
弎夜完成签到,获得积分10
27秒前
O-M175发布了新的文献求助10
27秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
Research on Disturbance Rejection Control Algorithm for Aerial Operation Robots 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038388
求助须知:如何正确求助?哪些是违规求助? 3576106
关于积分的说明 11374447
捐赠科研通 3305798
什么是DOI,文献DOI怎么找? 1819322
邀请新用户注册赠送积分活动 892672
科研通“疑难数据库(出版商)”最低求助积分说明 815029