Proof of the Contiguity Conjecture and Lognormal Limit for the Symmetric
Perceptron

v1v2 (latest)

Proof of the Contiguity Conjecture and Lognormal Limit for the Symmetric Perceptron

IEEE Annual Symposium on Foundations of Computer Science (FOCS), 2021

25 February 2021

ArXiv (abs)PDF HTML

Papers citing "Proof of the Contiguity Conjecture and Lognormal Limit for the Symmetric Perceptron"

12 / 12 papers shown

Title
Binary perceptron computational gap -- a parametric fl RDT view Mihailo Stojnic 68 1 0 02 Nov 2025
High-dimensional manifold of solutions in neural networks: insights from statistical physics Enrico M. Malatesta 274 5 0 20 Feb 2025
Injectivity capacity of ReLU gates Mihailo Stojnic 161 3 0 28 Oct 2024
Exact full-RSB SAT/UNSAT transition in infinitely wide two-layer neural networksSciPost Physics (SciPost Phys.), 2024 B. Annesi Enrico M. Malatesta Francesco Zamponi 227 7 0 09 Oct 2024
Fl RDT based ultimate lowering of the negative spherical perceptron capacity M. Stojnic 93 8 0 27 Dec 2023
Binary perceptrons capacity via fully lifted random duality theory M. Stojnic 216 10 0 29 Nov 2023
Typical and atypical solutions in non-convex neural networks with discrete and continuous weightsPhysical Review E (PRE), 2023 Carlo Baldassi Enrico M. Malatesta Gabriele Perugini R. Zecchina MQ 237 21 0 26 Apr 2023
Sharp analysis of EM for learning mixtures of pairwise differencesAnnual Conference Computational Learning Theory (COLT), 2023 A. Dhawan Cheng Mao A. Pananjady 201 1 0 20 Feb 2023
Disordered Systems Insights on Computational HardnessJournal of Statistical Mechanics: Theory and Experiment (JSTAT), 2022 D. Gamarnik Cristopher Moore Lenka Zdeborová AI4CE 214 52 0 15 Oct 2022
Equivalence between algorithmic instability and transition to replica symmetry breaking in perceptron learning systemsPhysical Review Research (Phys. Rev. Res.), 2021 Yang Zhao Junbin Qiu Mingshan Xie Haiping Huang 215 4 0 26 Nov 2021
Binary perceptron: efficient algorithms can find solutions in a rare well-connected clusterSymposium on the Theory of Computing (STOC), 2021 Emmanuel Abbe Shuangping Li Allan Sly MQ 165 41 0 04 Nov 2021
Learning through atypical "phase transitions" in overparameterized neural networks Carlo Baldassi Clarissa Lauditi Enrico M. Malatesta R. Pacelli Gabriele Perugini R. Zecchina 276 31 0 01 Oct 2021