Mutual Information in Rank-One Matrix Estimation

March 28, 2016 Β· Declared Dead Β· πŸ› Information Theory Workshop

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Florent Krzakala, Jiaming Xu, Lenka ZdeborovΓ‘ arXiv ID 1603.08447 Category cs.IT: Information Theory Cross-listed cond-mat.dis-nn, math.ST Citations 82 Venue Information Theory Workshop Last Checked 5 months ago
Abstract
We consider the estimation of a n-dimensional vector x from the knowledge of noisy and possibility non-linear element-wise measurements of xxT , a very generic problem that contains, e.g. stochastic 2-block model, submatrix localization or the spike perturbation of random matrices. We use an interpolation method proposed by Guerra and later refined by Korada and Macris. We prove that the Bethe mutual information (related to the Bethe free energy and conjectured to be exact by Lesieur et al. on the basis of the non-rigorous cavity method) always yields an upper bound to the exact mutual information. We also provide a lower bound using a similar technique. For concreteness, we illustrate our findings on the sparse PCA problem, and observe that (a) our bounds match for a large region of parameters and (b) that it exists a phase transition in a region where the spectum remains uninformative. While we present only the case of rank-one symmetric matrix estimation, our proof technique is readily extendable to low-rank symmetric matrix or low-rank symmetric tensor estimation
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Information Theory

Died the same way β€” πŸ‘» Ghosted