PAC-Bayesian matrix completion with a spectral scaled Student prior
We study the problem of matrix completion in this paper. A spectral scaled Student prior is exploited to favour the underlying low-rank structure of the data matrix. We provide a thorough theoretical investigation for our approach through PAC-Bayesian bounds. More precisely, our PAC-Bayesian approach enjoys a minimax-optimal oracle inequality which guarantees that our method works well under model misspecification and under general sampling distribution. Interestingly, we also provide efficient gradient-based sampling im- plementations for our approach by using Langevin Monte Carlo. More specifically, we show that our algorithms are significantly faster than Gibbs sampler in this problem. To illustrate the attractive features of our inference strategy, some numerical simulations are conducted and an application to image inpainting is demonstrated.
Code (0)
등록된 구현이 없습니다.
Tasks
Image InpaintingMatrix CompletionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PAC-Bayesian Matrix Completion with a Spectral Scaled Student Prior
We study the problem of matrix completion in this paper. A spectral scaled Student prior is exploited to favour the underlying low-rank structure of the data matrix. We provide a thorough theoretical investigation for ou…
Image InpaintingMatrix CompletionConcentration properties of fractional posterior in 1-bit matrix completion
The problem of estimating a matrix based on a set of its observed entries is commonly referred to as the matrix completion problem. In this work, we specifically address the scenario of binary observations, often termed …
Matrix CompletionBayesian Matrix Completion via Adaptive Relaxed Spectral Regularization
Bayesian matrix completion has been studied based on a low-rank matrix factorization formulation with promising results. However, little work has been done on Bayesian matrix completion based on the more direct spectral …
Bayesian InferenceCollaborative FilteringMatrix CompletionScaled Gradients on Grassmann Manifolds for Matrix Completion
This paper describes gradient methods based on a scaled metric on the Grassmann manifold for low-rank matrix completion. The proposed methods significantly improve canonical gradient methods especially on ill-conditioned…
Low-Rank Matrix CompletionMatrix CompletionScaled stochastic gradient descent for low-rank matrix completion
The paper looks at a scaled variant of the stochastic gradient descent algorithm for the matrix completion problem. Specifically, we propose a novel matrix-scaling of the partial derivatives that acts as an efficient pre…
Low-Rank Matrix CompletionMatrix Completion