DeepAI AI Chat
Log In Sign Up

Beyond Lazy Training for Over-parameterized Tensor Decomposition

by   Xiang Wang, et al.

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)^⊗ l of rank r (where r≪ 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 = Ω(d^l-1), while a variant of gradient descent can find an approximate tensor when m = O^*(r^2.5llog 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.


page 1

page 2

page 3

page 4


Experimental observation on a low-rank tensor model for eigenvalue problems

Here we utilize a low-rank tensor model (LTM) as a function approximator...

Understanding Deflation Process in Over-parametrized Tensor Decomposition

In this paper we study the training dynamics for gradient flow on over-p...

Beating the Perils of Non-Convexity: Guaranteed Training of Neural Networks using Tensor Methods

Training neural networks is a challenging non-convex optimization proble...

Gradient-based Optimization for Regression in the Functional Tensor-Train Format

We consider the task of low-multilinear-rank functional regression, i.e....

Big Neural Networks Waste Capacity

This article exposes the failure of some big neural networks to leverage...

Rethinking Gauss-Newton for learning over-parameterized models

Compared to gradient descent, Gauss-Newton's method (GN) and variants ar...

Strongly-Typed Agents are Guaranteed to Interact Safely

As artificial agents proliferate, it is becoming increasingly important ...