Exact storage capacity of dense associative memories with p-body interactions
36No. 1,367 in all physics · No. 32 in Statistical and Nonlinear Physics
A Hopfield network stores patterns as low points of an energy, and replacing pairwise couplings by couplings among p units at once lets it store vastly more patterns. The exact number of patterns it can store and still recall from a corrupted cue has not been computed with proof.
Status in the literature
Unverified note: it names recent work and was partly written without a live literature search; it awaits a check by an editor.
The scaling $P \sim N^{p-1}$ and a replica prediction of $\alpha_{c}(p)$ date to 1987 (Gardner, J. Phys. A 20, 3453, DOI 10.1088/0305-4470/20/11/046), the model was revived as dense associative memory by Krotov and Hopfield (2016), fixed-point capacity of order $N^{p-1}/\ln N$ is proved, and the exponential-interaction version was solved by replica methods (Lucibello and Mezard, PRL 2024); no rigorous derivation of $\alpha_{c}(p)$ at P proportional to $N^{p-1}$ was located (2026).
No solutions, ideas or subproblems yet.
See also
- Related Replica symmetry breaking in multimode-cavity spin glasses
- Related Do real circuits store memories at the theoretical capacity?
Details, signature and history
- Kind
- Well-posed question
- Answer
- Value
- Posed
- 1987
- Topic review
- L. Zdeborova and F. Krzakala, Statistical physics of inference: thresholds and algorithms, Advances in Physics 65, 2016. Link
- Record
- Revision 1 · imported from the seed collection · compiled by AI, not yet reviewed by an editor
Proof
- Fingerprint
- f17940bf88d2…
- Public log
- Entry 2,091, in checkpoint 2,123
- In the log by
- Block 969,698, 2026-10-03
This text was in the PubPhys log by that date. The date says nothing about when the problem was first posed.
Comments (0)
Comments are not records: they are not signed, stamped or logged. How comments work
No comments yet.
Sign in to comment.