Research map / Learning theory and algorithms / Sample complexity
Learning Opinions in Social Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Restrict the network to be deterministic (single realization) and use a VC-based ERM over the reachability hypothesis class | Deterministic social networks · Theoretical (sample complexity) | sample complexity m = O((VC(G) log(1/ε) + log(1/δ))/ε) | Helped |
| Use a random live-edge graph with no stability assumption (poorly concentrated random chain network) | Random social networks · Theoretical lower bound (random chain construction) | samples needed to recover a fixed node's state with probability 9/10 | Hurt |
| Add stability assumption ((ε0,δ0)-stability) and run the multi-sample-graph ERM plus majority-vote algorithm instead of a single ERM | Random social networks · Theoretical (sample complexity bound) | sample complexity m = O((E[VC(G)] log(1/ε) + log(1/δ))/ε) | Helped |
Closest papers by meaning
- Sample Complexity of Linear Regression Models for Opinion Formation in Networks (AAAI 2025 · similarity 0.89)
- Opinion Maximization in Social Networks by Modifying Internal Opinions (NeurIPS 2025 · similarity 0.86)
- Fast Computation and Optimization for Opinion-Based Quantities of Friedkin-Johnsen Model (NeurIPS 2025 · similarity 0.84)
- Optimizing Social Network Interventions via Hypergradient-Based Recommender System Design (ICML 2025 · similarity 0.83)
- Robust Offline Active Learning on Graphs (NeurIPS 2024 · similarity 0.83)
- Eliminating Majority Illusion Is Easy (AAAI 2025 · similarity 0.82)
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.