 Home
 Search Results
 Page 1 of 1
Search for: All records

Total Resources1
 Resource Type

10
 Availability

10
 Author / Contributor
 Filter by Author / Creator


Bolthausen, E. (1)

Nakajima, S (1)

Sun, N (1)

Xu, C (1)

#Tyler Phillips, Kenneth E. (0)

& Ahmed, Khadija. (0)

& AkcilOkan, O. (0)

& Akuom, D. (0)

& Aleven, V. (0)

& AndrewsLarson, C. (0)

& Archibald, J. (0)

& Attari, S. Z. (0)

& Ayala, O. (0)

& Babbitt, W. (0)

& Baek, Y. (0)

& Bahabry, Ahmed. (0)

& Bai, F. (0)

& Balasubramanian, R. (0)

& BarthCohen, L. (0)

& Bassett, L. (0)

 Filter by Editor


& Spizer, S. M. (0)

& . Spizer, S. (0)

& Ahn, J. (0)

& Bateiha, S. (0)

& Bosch, N. (0)

& Chen, B. (0)

& Chen, Bodong (0)

& Drown, S. (0)

& Higgins, A. (0)

& Kali, Y. (0)

& RuizArias, P.M. (0)

& S. Spitzer (0)

& Spitzer, S. (0)

& Spitzer, S.M. (0)

:Chaosong Huang, Gang Lu (0)

A. Beygelzimer (0)

A. E. Lischka, E.B. Dyer (0)

A. Ghate, K. Krishnaiyer (0)

A. Higgins (0)

A. I. Sacristán, J. C. (0)


Have feedback or suggestions for a way to improve these results?
!
Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher.
Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?
Some links on this page may take you to nonfederal websites. Their policies may differ from this site.

We consider the Ising perceptron model with N spins and M = N*alpha patterns, with a general activation function U that is bounded above. For U bounded away from zero, or U a onesided threshold function, it was shown by Talagrand (2000, 2011) that for small densities alpha, the free energy of the model converges in the largeN limit to the replica symmetric formula conjectured in the physics literature (Krauth–Mezard 1989, see also Gardner–Derrida 1988). We give a new proof of this result, which covers the more general class of all functions U that are bounded above and satisfy a certain variance bound. The proof uses the (first and second) moment method conditional on the approximate message passing iterates of the model. In order to deduce our main theorem, we also prove a new concentration result for the perceptron model in the case where U is not bounded away from zero.