paper-with-me

Papers

Low-rank matrix recovery with non-quadratic loss: projected gradient method and regularity projection oracle

2020-08-31 · Lijun Ding, Yuqian Zhang, Yudong Chen

Existing results for low-rank matrix recovery largely focus on quadratic loss, which enjoys favorable properties such as restricted strong convexity/smoothness (RSC/RSM) and well conditioning over all low rank matrices. However, many interesting problems involve more general, non-quadratic losses, which do not satisfy such properties. For these problems, standard nonconvex approaches such as rank-constrained projected gradient descent (a.k.a. iterative hard thresholding) and Burer-Monteiro factorization could have poor empirical performance, and there is no satisfactory theory guaranteeing global and fast convergence for these algorithms. In this paper, we show that a critical component in provable low-rank recovery with non-quadratic loss is a regularity projection oracle. This oracle restricts iterates to low-rank matrices within an appropriate bounded set, over which the loss function is well behaved and satisfies a set of approximate RSC/RSM conditions. Accordingly, we analyze an (averaged) projected gradient method equipped with such an oracle, and prove that it converges globally and linearly. Our results apply to a wide range of non-quadratic low-rank estimation problems including one bit matrix sensing/completion, individualized rank aggregation, and more broadly generalized linear models with rank constraints.

📄 PDF Abstract BibTeX arXiv:2008.13777

Code (0)

등록된 구현이 없습니다.

Tasks

Matrix Completion

Similar Papers 제목 키워드 기반

Projected Robust PCA with Application to Smooth Image Recovery

2020-07-21 · Long Feng, Junhui Wang

Most high-dimensional matrix recovery problems are studied under the assumption that the target matrix has certain intrinsic structures. For image data related matrix recovery problems, approximate low-rankness and smoot…

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

A Unified Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix Recovery

2017-08-01 · ICML 2017 8 · Lingxiao Wang, Xiao Zhang, Quanquan Gu

We propose a generic framework based on a new stochastic variance-reduced gradient descent algorithm for accelerating nonconvex low-rank matrix recovery. Starting from an appropriate initial estimator, our proposed …

A Universal Variance Reduction-Based Catalyst for Nonconvex Low-Rank Matrix Recovery

2017-01-09 · Lingxiao Wang, Xiao Zhang, Quanquan Gu

We propose a generic framework based on a new stochastic variance-reduced gradient descent algorithm for accelerating nonconvex low-rank matrix recovery. Starting from an appropriate initial estimator, our proposed algor…

A framework to generate sparsity-inducing regularizers for enhanced low-rank matrix completion

2023-10-08 · Zhi-Yong Wang, Hing Cheung So

Applying half-quadratic optimization to loss functions can yield the corresponding regularizers, while these regularizers are usually not sparsity-inducing regularizers (SIRs). To solve this problem, we devise a framewor…

Low-Rank Matrix CompletionMatrix Completion