.png){kind=icon}
返回
LEVEL SET LEARNING WITH PSEUDOREVERSIBLE NEURAL NETWORKS FOR NONLINEAR DIMENSION REDUCTION IN FUNCTION APPROXIMATION
.png){kind=icon}
OA
AI
DOI：10.1137/21M1459198.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Due to the curse of dimensionality and the limitation on training data, approximating high-dimensional functions is a very challenging task even for powerful deep neural networks. Inspired by the Nonlinear Level-set Learning (NLL) method, which uses the reversible residual network (RevNet), in this paper, we propose a new method of Dimension Reduction via Learning Level Sets (DRiLLS) for function approximation. Our method contains two major components: one is the pseudoreversible neural network (PRNN) module, which effectively transforms high-dimensional input variables to low-dimensional active variables, and the other is the synthesized regression module for approximating function values based on the transformed data in the low-dimensional space. The PRNN not only relaxes the invertibility constraint of the nonlinear transformation present in the NLL method due to the use of RevNet but also adaptively weights the influence of each sample and controls the sensitivity of the function to the learned active variables. The synthesized regression uses Euclidean distance in the input space to select neighboring samples whose projections on the space of active variables are used to perform local least-squares polynomial fitting. This helps to resolve numerical oscillation issues present in traditional local and global regressions. Extensive experimental results demonstrate that our DRiLLS method outperforms both the NLL and active subspace methods, especially when the target function possesses critical points in the interior of its input domain.
Keyword:
function approximation
dimension reduction
pseudoreversible neural network
level set learning
synthesized regression
sparse data
期刊
IF:
2.6
论文数:
5.1K
被引数:
1.8W
机构
引用论文
Dual-template strategy synthesis of hierarchically porous electrocatalysts for oxygen reduction reaction用于氧还原反应的分级多孔电催化剂的双模板策略合成
OAAI
.png){kind=icon}
OAAI分享收藏Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification深度UQ: 学习用于高维不确定性量化的深度神经网络代理模型OAAI
OAAI分享收藏Measuring the current distribution in a 10 m long high temperature superconducting cable conductor测量一根10米长高温超导电缆导体中的电流分布
PREAI
分享收藏
查看更多内容