en-de
en-es
en-fr
en-pt
en-sl
en
en-zh
0.25
0.5
0.75
1.25
1.5
1.75
2
Concentration-Based Guarantees for Low-Rank Matrix Reconstruction
Published on Aug 02, 20113992 Views
We consider the problem of approximately reconstructing a partially-observed, approximately low-rank matrix. This problem has received much attention lately, mostly using the trace-norm as a surroga
Related categories
Chapter list
Concentration-Based Guarantees for Low-Rank Matrix Reconstruction00:00
Low-rank matrix reconstruction - 100:21
Low-rank matrix reconstruction - 200:45
Low-rank matrix reconstruction - 301:26
Low-rank matrix reconstruction - 402:31
Low-rank matrix reconstruction - 503:22
Low-rank matrix reconstruction - 603:37
Trace-norm and max-norm - 104:10
Trace-norm and max-norm - 204:58
Trace-norm and max-norm - 305:31
Bounds on Rademacher complexity - 106:50
Bounds on Rademacher complexity - 208:06
Low-rank matrix reconstruction under absolute-error loss - 108:41
Low-rank matrix reconstruction under absolute-error loss - 209:07
Low-rank matrix reconstruction under absolute-error loss - 309:15
Low-rank matrix reconstruction under absolute-error loss - 409:38
Low-rank matrix reconstruction under absolute-error loss - 509:46
Learning guarantees - 110:02
Low-rank matrix reconstruction under squared-error loss - 110:17
Low-rank matrix reconstruction under squared-error loss - 210:36
Low-rank matrix reconstruction under squared-error loss - 310:45
Learning guarantees - 211:32
Trace-norm vs. max-norm - 111:57
Trace-norm vs. max-norm - 212:28
Learning guarantees - 313:02
Sampling & noise models - 113:34
Sampling & noise models - 213:58
Sampling & noise models - 314:19
Sampling & noise models - 415:03
Comparison of results - 115:57
Comparison of results - 216:25
Comparison of results - 316:56
Comparison of results - 417:44
Comparison of results - 518:26
Comparison of results - 619:14
Summary - 119:43
Summary - 220:24