DeepAI AI Chat
Log In Sign Up

Deep Unfolded Tensor Robust PCA with Self-supervised Learning

by   Harry Dong, et al.
Carnegie Mellon University

Tensor robust principal component analysis (RPCA), which seeks to separate a low-rank tensor from its sparse corruptions, has been crucial in data science and machine learning where tensor structures are becoming more prevalent. While powerful, existing tensor RPCA algorithms can be difficult to use in practice, as their performance can be sensitive to the choice of additional hyperparameters, which are not straightforward to tune. In this paper, we describe a fast and simple self-supervised model for tensor RPCA using deep unfolding by only learning four hyperparameters. Despite its simplicity, our model expunges the need for ground truth labels while maintaining competitive or even greater performance compared to supervised deep unfolding. Furthermore, our model is capable of operating in extreme data-starved scenarios. We demonstrate these claims on a mix of synthetic data and real-world tasks, comparing performance against previously studied supervised deep unfolding methods and Bayesian optimization baselines.


page 5

page 7

page 8


Fast Robust Tensor Principal Component Analysis via Fiber CUR Decomposition

We study the problem of tensor robust principal component analysis (TRPC...

Principal Component Analysis with Tensor Train Subspace

Tensor train is a hierarchical tensor network structure that helps allev...

Efficient Tensor Robust PCA under Hybrid Model of Tucker and Tensor Train

Tensor robust principal component analysis (TRPCA) is a fundamental mode...

Fast and Provable Tensor Robust Principal Component Analysis via Scaled Gradient Descent

An increasing number of data science and machine learning problems rely ...

Global Weighted Tensor Nuclear Norm for Tensor Robust Principal Component Analysis

Tensor Robust Principal Component Analysis (TRPCA), which aims to recove...

AugmentedPCA: A Python Package of Supervised and Adversarial Linear Factor Models

Deep autoencoders are often extended with a supervised or adversarial lo...

Efficient AutoML Pipeline Search with Matrix and Tensor Factorization

Data scientists seeking a good supervised learning model on a new datase...