论文笔记：Efficient Nonconvex Regularized Tensor Completion with Structure-aware Proximal Iterations
一、本文创新点 1、作者注意到重叠核范数对于张量补全的效果比较好，提出了一种用于张量补全的重叠核范数正则化的非凸变体。 2、该正则化自然引起损失函数的非凸，故提出了一个更有效的优化的算法 3、提出的优化算法有三点优势：一：避免了代价昂贵的张量展开和合并；二：在迭代中保持“稀疏加低秩”结构；三：融入适应的动力。 二、相关工作 1、低秩矩阵学习
相关文章
- 1. 论文笔记 ：Tensor Factorization for Low-Rank Tensor Completion
- 2. 论文笔记：Higher-dimension Tensor Completion via Low-rank Tensor Ring Decomposition
- 3. 论文笔记：Coupled Tensor Completion via Low-rank Tensor Ring
- 4. 论文笔记Globally and Locally Consistent Image Completion
- 5. 论文笔记：Tensor Ring Decomposition with Rank Minimization on Latent Space
- 6. 【阅读笔记】Reasoning With Neural Tensor Networks for Knowledge Base Completion
- 7. 论文笔记：Graph Convolutional Matrix Completion
- 8. Unsupervised Deep Image Fusion With Structure Tensor Representations论文笔记
- 9. 论文笔记：Efficient Graph-Based Image Segmentation
- 10. SteReFo: Efficient Image Refocusing with Stereo Vision 论文笔记
- 更多相关文章...
- • ASP.NET Razor - 标记 - ASP.NET 教程
- • CAP理论是什么？ - NoSQL教程
- • Tomcat学习笔记（史上最全tomcat学习笔记）
- • Scala 中文乱码解决
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 论文笔记 ：Tensor Factorization for Low-Rank Tensor Completion
- 2. 论文笔记：Higher-dimension Tensor Completion via Low-rank Tensor Ring Decomposition
- 3. 论文笔记：Coupled Tensor Completion via Low-rank Tensor Ring
- 4. 论文笔记Globally and Locally Consistent Image Completion
- 5. 论文笔记：Tensor Ring Decomposition with Rank Minimization on Latent Space
- 6. 【阅读笔记】Reasoning With Neural Tensor Networks for Knowledge Base Completion
- 7. 论文笔记：Graph Convolutional Matrix Completion
- 8. Unsupervised Deep Image Fusion With Structure Tensor Representations论文笔记
- 9. 论文笔记：Efficient Graph-Based Image Segmentation
- 10. SteReFo: Efficient Image Refocusing with Stereo Vision 论文笔记