Sharp threshold sequence and universality for Ising perceptron models
Shuta Nakajima, Nike Sun
Abstract
We study a family of Ising perceptron models with 0,1-valued activation functions. This includes the classical half-space models, as well as some of the symmetric models considered in recent works. For each of these models we show that the free energy is self-averaging, there is a sharp threshold sequence, and the free energy is universal with respect to the disorder. A prior work of C. Xu (2019) used very different methods to show a sharp threshold sequence in the half-space Ising perceptron with Bernoulli disorder. Recent works of Perkins-Xu (2021) and Abbe-Li-Sly (2021) determined the sharp threshold and limiting free energy in a symmetric perceptron model. The results of this paper apply in more general settings, and are based on new “add one constraint” estimates extending Talagrand's estimates for the half-space model (1999, 2011). * The full version of the paper can be accessed at https://arxiv.org/abs/2204.03469.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 3dbe3f0b-0812-485b-bd99-c5fe3f41fa6cCited by top-tier papers3
- Distribution of the threshold for the symmetric perceptronAshwin Sah, Mehtaab SawhneyFOCS 2023 · 6 citations
- Capacity Threshold for the Ising PerceptronBrice HuangFOCS 2024 · 4 citations
- Discrepancy Algorithms for the Binary PerceptronShuangping Li, Tselil Schramm, Kangjie ZhouSTOC 2025 · 1 citation
Builds on5
- Frozen 1-RSB structure of the symmetric Ising perceptronWill Perkins, Changji XuSTOC 2021 · 31 citations
- Proof of the Contiguity Conjecture and Lognormal Limit for the Symmetric PerceptronEmmanuel Abbe, Shuangping Li, Allan SlyFOCS 2021 · 27 citations
- Algorithms and Barriers in the Symmetric Binary Perceptron ModelDavid Gamarnik, Eren C. Kizildag, Will Perkins, Changji XuFOCS 2022 · 26 citations
- Binary perceptron: efficient algorithms can find solutions in a rare well-connected clusterEmmanuel Abbe, Shuangping Li, Allan SlySTOC 2022 · 23 citations
- Discrepancy minimization via a self-balancing walkRyan Alweiss, Yang P. Liu, Mehtaab SawhneySTOC 2021 · 17 citations
Related papers
- Locally Sampleable Uniform Symmetric DistributionsDaniel M. Kane, Anthony Ostuni, Kewen WuSTOC 2025 · 4 citations
- Symmetric Perceptrons, Number Partitioning and LatticesNeekon Vafa, Vinod VaikuntanathanSTOC 2025 · 1 citation
- Computational thresholds for the fixed-magnetization Ising modelCharlie Carlson, Ewan Davies, Alexandra Kolla, Will PerkinsSTOC 2022 · 3 citations
- On the Universality of Rotation Equivariant Point Cloud NetworksNadav Dym, Haggai MaronICLR 2021 · 22 citations
- Separation Power of Equivariant Neural NetworksMarco Pacini, Xiaowen Dong, Bruno Lepri, Gabriele SantinICLR 2025
