A note on the capacity of the binary perceptron
Abstract: Determining the capacity $\alpha_c$ of the Binary Perceptron is a long-standing problem. Krauth and Mezard (1989) conjectured an explicit value of $\alpha_c$, approximately equal to .833, and a rigorous lower bound matching this prediction was recently established by Ding and Sun (2019). Regarding the upper bound, Kim and Roche (1998) and Talagrand (1999) independently showed that $\alpha_c$ < .996, while Krauth and Mezard outlined an argument which can be used to show that $\alpha_c$ < .847. The purpose of this expository note is to record a complete proof of the bound $\alpha_c$ < .847. The proof is a conditional first moment method combined with known results on the spherical perceptron
- Altschuler, D. J. Zero-one laws for random feasibility problems. arXiv preprint arXiv:2309.13133 (2023).
- Capacity lower bound for the Ising perceptron. In STOC’19—Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing (2019), ACM, New York, pp. 816–827.
- Gardner, E. Maximum storage capacity in neural networks. Europhysics letters 4, 4 (1987), 481.
- Gardner, E. The space of interactions in neural network models. J. Phys. A 21, 1 (1988), 257–270.
- Optimal storage properties of neural network models. J. Phys. A 21, 1 (1988), 271–284.
- On the optimal capacity of binary neural networks: Rigorous combinatorial approaches. In Proceedings of the eighth annual Conference on Learning Theory (1995), pp. 240–249.
- Storage capacity of memory networks with binary couplings. Journal de Physique 50, 20 (1989), 3057–3066.
- Sharp threshold sequence and universality for Ising perceptron models. In Proceedings of the 2023 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA) (2023), SIAM, Philadelphia, PA, pp. 638–674.
- On the volume of the intersection of a sphere with random half spaces. C. R. Math. Acad. Sci. Paris 334, 9 (2002), 803–806.
- Talagrand, M. Intersecting random half cubes. vol. 15. 1999, pp. 436–449. Statistical physics methods in discrete probability, combinatorics, and theoretical computer science (Princeton, NJ, 1997).
- Talagrand, M. Mean field models for spin glasses. Volume I. Springer-Verlag, Berlin, 2011.
- Talagrand, M. Mean field models for spin glasses. Volume II. Springer, Heidelberg, 2011.
- Xu, C. Sharp threshold for the Ising perceptron model. Ann. Probab. 49, 5 (2021), 2399–2415.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
