Beyond Lazy Training for Over-parameterized Tensor Decomposition
원문 초록
Over-parametrization is an important technique in training neural networks. In both theory and practice, training a larger network allows the optimization algorithm to avoid bad local optimal solutions. In this paper we study a closely related tensor decomposition problem: given an $l$-th order tensor in $(R^d)^{\otimes l}$ of rank $r$ (where $r\ll d$), can variants of gradient descent find a rank $m$ decomposition where $m > r$? We show that in a lazy training regime (similar to the NTK regime for neural networks) one needs at least $m = \Omega(d^{l-1})$, while a variant of gradient descent can find an approximate tensor when $m = O^*(r^{2.5l}\log d)$. Our results show that gradient descent on over-parametrized objective could go beyond the lazy training regime and utilize certain low-rank structure in the data.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Revisit CP Tensor Decomposition: Statistical Optimality and Fast Convergence
D-Tracker: Modeling Interest Diffusion in Social Activity Tensor Data Streams
Multiscale Tensor Summation Factorization as a New Neural Network Layer (MTS Layer) for Multidimensional Data Processing
Knowledge Graph Completion with Mixed Geometry Tensor Factorization
Coeff-Tuning: A Graph Filter Subspace View for Tuning Attention-Based Large Models
Guaranteed Multidimensional Time Series Prediction via Deterministic Tensor Completion Theory
토론
이 논문과 연결된 포럼 글이 아직 없습니다.