paper-with-me

홈 › Papers

A Validation Approach to Over-parameterized Matrix and Image Recovery

2022-09-21 · Lijun Ding, Zhen Qin, Liwei Jiang, Jinxin Zhou, Zhihui Zhu

This paper studies the problem of recovering a low-rank matrix from several noisy random linear measurements. We consider the setting where the rank of the ground-truth matrix is unknown a priori and use an objective function built from a rank-overspecified factored representation of the matrix variable, where the global optimal solutions overfit and do not correspond to the underlying ground truth. We then solve the associated nonconvex problem using gradient descent with small random initialization. We show that as long as the measurement operators satisfy the restricted isometry property (RIP) with its rank parameter scaling with the rank of the ground-truth matrix rather than scaling with the overspecified matrix rank, gradient descent iterations are on a particular trajectory towards the ground-truth matrix and achieve nearly information-theoretically optimal recovery when it is stopped appropriately. We then propose an efficient stopping strategy based on the common hold-out method and show that it detects a nearly optimal estimator provably. Moreover, experiments show that the proposed validation approach can also be efficiently used for image restoration with deep image prior, which over-parameterizes an image with a deep network.

📄 PDF Abstract BibTeX arXiv:2209.10675

Code (0)

등록된 구현이 없습니다.

Tasks

Image Restoration

Methods 이 논문이 사용한 방법론

Early Stopping Early Stopping is a regularization technique for deep neural networks that stops training when parameter updates no longer begin to yield improves on a validation set. In…

Similar Papers 제목 키워드 기반

Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization

2020-06-16 · NeurIPS 2020 12 · Chong You, Zhihui Zhu, Qing Qu, Yi Ma

Recent advances have shown that implicit bias of gradient descent on over-parameterized models enables the recovery of low-rank matrices from linear measurements, even with no prior knowledge on the intrinsic rank. In co…

Flat minima generalize for low-rank matrix recovery

2022-03-07 · Lijun Ding, Dmitriy Drusvyatskiy, Maryam Fazel, Zaid Harchaoui

Empirical evidence suggests that for a variety of overparameterized nonlinear models, most notably in neural network training, the growth of the loss around a minimizer strongly impacts its performance. Flat minima -- th…

Matrix Completion

Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably

2022-02-07 · Tianyi Liu, Yan Li, Enlu Zhou, Tuo Zhao

We investigate the role of noise in optimization algorithms for learning over-parameterized models. Specifically, we consider the recovery of a rank one matrix $Y^*\in R^{d\times d}$ from a noisy observation $Y$ using an…

Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact Recovery

2021-09-23 · NeurIPS 2021 12 · Lijun Ding, Liwei Jiang, Yudong Chen, Qing Qu 외

We study the robust recovery of a low-rank matrix from sparsely and grossly corrupted Gaussian measurements, with no prior knowledge on the intrinsic rank. We consider the robust matrix factorization approach. We employ …

Sign-RIP: A Robust Restricted Isometry Property for Low-rank Matrix Recovery

2021-02-05 · Jianhao Ma, Salar Fattahi

Restricted isometry property (RIP), essentially stating that the linear measurements are approximately norm-preserving, plays a crucial role in studying low-rank matrix recovery problem. However, RIP fails in the robust …