AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Generalized Nonbacktracking Bounds on the Influence

Emmanuel Abbe, Sanjeev Kulkarni, Eun Jee Lee

JMLR 2020 · Learning theory and algorithms › Sample complexity · approach: Computational thresholds in graphs and structure · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use nonbacktracking upper bound NB-UB instead of spectral upper boundinfluence upper bound in independent cascade · Erdos-Renyi and random 3-regular networks (n=1000)average relative gap to Monte CarloImproved
use NB-UB instead of spectral upper boundinfluence upper bound · scale-free networks (n=1000)average relative gapNo clear effect
use NB-LB instead of 10-sample Monte Carlo probabilistic lower boundinfluence lower bound · Erdos-Renyi, scale-free, regular networks, p < 0.4average relative gapImproved
increase nonbacktracking length r from 2 to 3, 4, 5 (ablation)r-nonbacktracking upper bound · small-world network SW(1000,4,0.01), p in [0.32, 0.42]upper bound tightnessImproved
increase Monte Carlo sample size N from 5 to 3000 (ablation)probabilistic MC upper bound · 3-regular network (n=1000)upper bound tightnessImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy