Robust Estimation for Random Graphs
Not on the map. Why?
Abstract (arXiv)
We study the problem of robustly estimating the parameter p of an ErdHos-R'enyi random graph on n nodes, where a γ fraction of nodes may be adversarially corrupted. After showing the deficiencies of canonical estimators, we design a computationally-efficient spectral algorithm which estimates p up to accuracy tilde O(√p(1-p)/n + γ√p(1-p) /√n+ γ/n) for γ < 1/60. Furthermore, we give an inefficient algorithm with similar accuracy for all γ <1/2, the information-theoretic limit. Finally, we prove a nearly-matching statistical lower bound, showing that the error of our algorithms is optimal up to logarithmic factors.
Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 35 of its 66 references that are in the map. First posted on arXiv 9 Nov 2021.
Builds on
35 of 66 references.
References · 35
- 2016Robust Estimators in High Dimensions without the Computational Intractabilitycited by 209
- 2016Agnostic Estimation of Mean and Covariancecited by 131
- 2018Sever: A Robust Meta-Algorithm for Stochastic Optimizationcited by 125
- 2019Recent Advances in Algorithmic High-Dimensional Robust Statisticscited by 101
- 2016Learning from Untrusted Datacited by 90
- 2017Being Robust (in High Dimensions) Can Be Practicalcited by 83
- 2017Mixture Models, Robustness, and Sum of Squares Proofscited by 81
- 2018Robust Estimation via Robust Gradient Estimationcited by 76
- 2018Efficient Algorithms for Outlier-Robust Regressioncited by 72
- 2017List-Decodable Robust Mean Estimation and Learning Mixtures of Spherical Gaussianscited by 70
- 2015Randomized Block Krylov Methods for Stronger and Faster Approximate Singular Value Decompositioncited by 64
- 2020Robust regression with covariate filtering: Heavy tails and adversarial contaminationcited by 50
23 more
- 2017Resilience: A Criterion for Learning in the Presence of Arbitrary Outlierscited by 43
- 2019Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier Detectioncited by 41
- 2017Robustly Learning a Gaussian: Getting Optimal Error, Efficientlycited by 39
- 2018High-Dimensional Robust Mean Estimation in Nearly-Linear Timecited by 39
- 2019Generalized Resilience and Robust Statisticscited by 37
- 2018High Dimensional Robust Sparse Regressioncited by 29
- 2019Faster Algorithms for High-Dimensional Robust Covariance Estimationcited by 28
- 2015How Robust are Reconstruction Thresholds for Community Detection?cited by 20
- 2014Robust and computationally feasible community detection in the presence of arbitrary outlier nodescited by 17
- 2015Private Graphon Estimation for Sparse Graphscited by 17
- 2020High-Dimensional Robust Mean Estimation via Gradient Descentcited by 16
- 2017Learning Discrete Distributions from Untrusted Batchescited by 14
- 2019Local Statistics, Semidefinite Programming, and Community Detectioncited by 14
- 2018Revealing Network Structure, Confidentially: Improved Rates for Node-Private Graphon Estimationcited by 13
- 2019Efficiently Estimating Erdos-Renyi Graphs with Node Differential Privacycited by 13
- 2015Sum-of-squares lower bounds for planted cliquecited by 12
- 2019Optimal Robust Learning of Discrete Distributions from Batchescited by 10
- 2015Improved Sum-of-Squares Lower Bounds for Hidden Clique and Hidden Submatrix Problemscited by 9
- 2016Robust Learning of Fixed-Structure Bayesian Networkscited by 8
- 2019Efficiently Learning Structured Distributions from Untrusted Batchescited by 8
- 2020Learning Structured Distributions From Untrusted Batches: Faster and Simplercited by 8
- 2020A General Method for Robust Learning from Batchescited by 8
- 2015Learning Communities in the Presence of Errorscited by 7
Built on by
Citing papers per year: 2022: 3; 2023: 2; 2024: 1; 2025: 2.
8 papers.
- 2022Minimax Rates for Robust Community Detectioncited by 12
- 2023Reaching Kesten-Stigum Threshold in the Stochastic Block Model under Node Corruptionscited by 7
- 2022Efficient List-Decodable Regression using Batchescited by 5
- 2022Robust estimation algorithms don't need to know the corruption levelcited by 4
- 2023Linear Regression using Heterogeneous Data Batchescited by 3
- 2024Private Edge Density Estimation for Random Graphs: Optimal, Efficient and Robustcited by 2
- 2025Improved Robust Estimation for ErdHos-R'enyi Graphs: The Sparse Regime and Optimal Breakdown Pointcited by 0
- 2025SubSearch: Robust Estimation and Outlier Detection for Stochastic Block Models via Subgraph Searchcited by 0
- 2025SubSearch: Robust Estimation and Outlier Detection for Stochastic Block Models via Subgraph Search4 Jun 2025
- 2025Improved Robust Estimation for ErdHos-R'enyi Graphs: The Sparse Regime and Optimal Breakdown Point5 Mar 2025
- 2024Private Edge Density Estimation for Random Graphs: Optimal, Efficient and Robust26 May 2024
- 2023Linear Regression using Heterogeneous Data Batches5 Sep 2023
- 2023Reaching Kesten-Stigum Threshold in the Stochastic Block Model under Node Corruptions17 May 2023
- 2022Efficient List-Decodable Regression using Batches23 Nov 2022
- 2022Minimax Rates for Robust Community Detection25 Jul 2022
- 2022Robust estimation algorithms don't need to know the corruption level11 Feb 2022