paper-with-me

Papers

LRSVRG-IMC: An SVRG-Based Algorithm for LowRank Inductive Matrix Completion

2022-01-21 · Shangrong Yu, Yuxin Chen, Hejun Wu

Low-rank inductive matrix completion (IMC) is currently widely used in IoT data completion, recommendation systems, and so on, as the side information in IMC has demonstrated great potential in reducing sample point remains a major obstacle for the convergence of the nonconvex solutions to IMC. What's more, carefully choosing the initial solution alone does not usually help remove the saddle points. To address this problem, we propose a stocastic variance reduction gradient-based algorithm called LRSVRG-IMC. LRSVRG-IMC can escape from the saddle points under various low-rank and sparse conditions with a properly chosen initial input. We also prove that LRSVVRG-IMC achieves both a linear convergence rate and a near-optimal sample complexity. The superiority and applicability of LRSVRG-IMC are verified via experiments on synthetic datasets.

📄 PDF Abstract BibTeX arXiv:2201.08516

Code (0)

등록된 구현이 없습니다.

Tasks

Matrix CompletionRecommendation Systems

Similar Papers 제목 키워드 기반

Improved SVRG for quadratic functions

2020-06-01 · Nabil Kahale

We analyse an iterative algorithm to minimize quadratic functions whose Hessian matrix $H$ is the expectation of a random symmetric $d\times d$ matrix. The algorithm is a variant of the stochastic variance reduced gradie…

Sequential Randomized Matrix Factorization for Gaussian Processes: Efficient Predictions and Hyper-parameter Optimization

2017-11-19 · Shaunak D. Bopardikar, George S. Eskander Ekladious

This paper presents a sequential randomized lowrank matrix factorization approach for incrementally predicting values of an unknown function at test points using the Gaussian Processes framework. It is well-known that in…

Computational EfficiencyGaussian Processes

Scalable Label Propagation for Multi-relational Learning on the Tensor Product of Graphs

2018-02-20 · Zhuliu Li, Raphael Petegrosso, Shaden Smith, David Sterling 외

Multi-relational learning on knowledge graphs infers high-order relations among the entities across the graphs. This learning task can be solved by label propagation on the tensor product of the knowledge graphs to learn…

Knowledge GraphsRelational Reasoning

Stochastic Low-Rank Bandits

2017-12-13 · Branislav Kveton, Csaba Szepesvari, Anup Rao, Zheng Wen 외

Many problems in computer vision and recommender systems involve low-rank matrices. In this work, we study the problem of finding the maximum entry of a stochastic low-rank matrix from sequential observations. At each st…

Recommendation Systems

A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimization

2018-02-13 · NeurIPS 2018 12 · Zhize Li, Jian Li

We analyze stochastic gradient algorithms for optimizing nonconvex, nonsmooth finite-sum problems. In particular, the objective function is given by the summation of a differentiable (possibly nonconvex) component, toget…