PulseAugur
EN
LIVE 11:54:34

New research details convex relaxations for graph alignment

A new research paper published on arXiv details advancements in convex relaxations for graph alignment problems. The study focuses on correlated Gaussian Orthogonal Ensemble (GOE) matrices, aiming to recover hidden vertex permutations. Researchers demonstrated that specific convex relaxations can accurately recover nearly all vertices when the correlation parameter meets certain conditions, thereby tightening prior results in the field. AI

RANK_REASON The cluster contains a research paper published on arXiv detailing theoretical advancements in graph alignment. [lever_c_demoted from research: ic=2 ai=0.4]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Laurent Massouli\'e, Sushil Mahavir Varma, Louis Vassaux, Ir\`ene Waldspurger ·

    Phase Transition in Convex Relaxations for Graph Alignment

    arXiv:2606.15581v1 Announce Type: cross Abstract: We study the graph alignment problem for correlated Gaussian Orthogonal Ensemble (GOE) matrices, where the goal is to recover a hidden vertex permutation given two correlated symmetric Gaussian matrices $(A, B)$ with correlation $…

  2. arXiv stat.ML TIER_1 English(EN) · Irène Waldspurger ·

    Phase Transition in Convex Relaxations for Graph Alignment

    We study the graph alignment problem for correlated Gaussian Orthogonal Ensemble (GOE) matrices, where the goal is to recover a hidden vertex permutation given two correlated symmetric Gaussian matrices $(A, B)$ with correlation $1/\sqrt{1+σ^2}$. While the maximum likelihood esti…