en-es
en
0.25
0.5
0.75
1.25
1.5
1.75
2
A New Convex Relaxation for Tensor Completion
Published on Nov 07, 20132623 Views
Tensor factorization has received a lot of interest recently in the collaborative filtering field, as a natural extension of matrix completion. That is due to the capability of tensors to model the re
Related categories
Chapter list
Multilinear Multitask Learning00:00
Outline00:16
Problem - 100:50
Problem - 201:38
Problem - 302:56
Transfer Learning04:08
Proposed solution: Multilinear Multitask Learning (MLMTL)04:45
Non-convex approach: Tucker decomposition06:25
Convex approach07:40
Alternating Direction Method of Multipliers (ADMM) - 108:09
Alternating Direction Method of Multipliers (ADMM) - 209:09
Experiments09:37
Remarks11:22
Rethinking the convex approach - 111:48
Rethinking the convex approach - 213:17
Rethinking the convex approach - 315:09
Rethinking the convex approach - 416:18
Experiments on tensor completion17:21
Conclusions19:28