Operator SVD with Neural Networks via Nested Low-Rank Approximation
CoRR(2024)
摘要
Computing eigenvalue decomposition (EVD) of a given linear operator, or
finding its leading eigenvalues and eigenfunctions, is a fundamental task in
many machine learning and scientific computing problems. For high-dimensional
eigenvalue problems, training neural networks to parameterize the
eigenfunctions is considered as a promising alternative to the classical
numerical linear algebra techniques. This paper proposes a new optimization
framework based on the low-rank approximation characterization of a truncated
singular value decomposition, accompanied by new techniques called nesting for
learning the top-L singular values and singular functions in the correct
order. The proposed method promotes the desired orthogonality in the learned
functions implicitly and efficiently via an unconstrained optimization
formulation, which is easy to solve with off-the-shelf gradient-based
optimization algorithms. We demonstrate the effectiveness of the proposed
optimization framework for use cases in computational physics and machine
learning.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要