Error estimates for DeepONets: a deep learning framework in infinite dimensions

作者
Samuel Lanthaler,Siddhartha Mishra,George Em Karniadakis
出处
期刊:Transactions of mathematics and its applications [Oxford University Press]
卷期号:6 (1) 被引量:176
标识
DOI:10.1093/imatrm/tnac001
摘要

Abstract DeepONets have recently been proposed as a framework for learning nonlinear operators mapping between infinite-dimensional Banach spaces. We analyze DeepONets and prove estimates on the resulting approximation and generalization errors. In particular, we extend the universal approximation property of DeepONets to include measurable mappings in non-compact spaces. By a decomposition of the error into encoding, approximation and reconstruction errors, we prove both lower and upper bounds on the total error, relating it to the spectral decay properties of the covariance operators, associated with the underlying measures. We derive almost optimal error bounds with very general affine reconstructors and with random sensor locations as well as bounds on the generalization error, using covering number arguments. We illustrate our general framework with four prototypical examples of nonlinear operators, namely those arising in a nonlinear forced ordinary differential equation, an elliptic partial differential equation (PDE) with variable coefficients and nonlinear parabolic and hyperbolic PDEs. While the approximation of arbitrary Lipschitz operators by DeepONets to accuracy $\epsilon $ is argued to suffer from a ‘curse of dimensionality’ (requiring a neural networks of exponential size in $1/\epsilon $), in contrast, for all the above concrete examples of interest, we rigorously prove that DeepONets can break this curse of dimensionality (achieving accuracy $\epsilon $ with neural networks of size that can grow algebraically in $1/\epsilon $).Thus, we demonstrate the efficient approximation of a potentially large class of operators with this machine learning framework.

科研通智能强力驱动
Strongly Powered by AbleSci AI
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
从容的子轩完成签到,获得积分10
1秒前
养殖发布了新的文献求助10
1秒前
1秒前
1秒前
今后的应助被回忆采纳,获得10
1秒前
orixero的应助被neversay4ever采纳,获得10
2秒前
2秒前
英吉利25发布了新的文献求助10
2秒前
彭静琳完成签到,获得积分10
2秒前
2秒前
乐乐的应助被热爱科研的小孩采纳,获得10
3秒前
西西歪完成签到,获得积分10
3秒前
3秒前
科研蛀虫完成签到,获得积分10
3秒前
4秒前
明乎坦涂完成签到,获得积分10
4秒前
酷波er的应助被corleeang采纳,获得10
5秒前
文静曼安发布了新的文献求助10
5秒前
5秒前
5秒前
5秒前
阎罗恶煞发布了新的文献求助10
6秒前
曾经的安珊完成签到,获得积分10
6秒前
6秒前
6秒前
6秒前
kimbrough发布了新的文献求助10
7秒前
Xiong完成签到,获得积分10
7秒前
zjz1发布了新的文献求助10
7秒前
7秒前
7秒前
0001发布了新的文献求助10
7秒前
ltt发布了新的文献求助10
7秒前
yyy完成签到,获得积分10
8秒前
8秒前
张建秀完成签到,获得积分10
10秒前
10秒前
彭静琳发布了新的文献求助10
10秒前
10秒前
wway完成签到 ,获得积分10
11秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183142
求助须知:如何正确求助?哪些是违规求助? 9572420
关于积分的说明 21825253
捐赠科研通 7779922
什么是DOI,文献DOI怎么找? 3433850
关于科研通互助平台的介绍 2558060
邀请新用户注册赠送积分活动 2480124