Max vs Min: Tensor Decomposition and ICA with nearly Linear Sample Complexity thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Max vs Min: Tensor Decomposition and ICA with nearly Linear Sample Complexity

Published on Aug 20, 20151533 Views

We present a simple, general technique for reducing the sample complexity of matrix and tensor decomposition algorithms applied to distributions. We use the technique to give a polynomial-time algorit

Related categories

Chapter list

Max vs Min: Tensor Decomposition and ICA with nearly Linear Sample Complexity00:00
Independent Component Analysis (ICA)00:24
Derivs of Fourier transform01:39
Quallity of eigendecomposition02:36
Our recursive technique03:17