Robust estimators in high dimensions without the computational intractability

DOI10.1109/FOCS.2016.85MaRDI QIDQ6946432zbMATH OpenFDO

Authors Jerry Zirui Li, Ilias Diakonikolas, Ankur Moitra, Daniel M. Kane, Gautam Kamath, Alistair Stewart

Publication date 6 August 2025

Full work available at URL https://hdl.handle.net/1721.1/126386

Mathematics Subject Classification ID

Algorithms in computer science (68Wxx) Discrete mathematics in relation to computer science (68Rxx) Theory of computing (68Qxx)

Cited in

(10)

• Robust Regression with Covariate Filtering: Heavy Tails and Adversarial Contamination
• Attribute-efficient learning of halfspaces with malicious noise: near-optimal label complexity and noise tolerance
• On the sample complexity of privately learning unbounded high-dimensional Gaussians
• Polynomial-time sum-of-squares can robustly estimate mean and covariance of Gaussians optimally
• Can adversarially robust learning leverage computational hardness?
• Sample efficient identity testing and independence testing of quantum states
• Buying data over time: approximately optimal strategies for dynamic data-driven decisions
• Nearly minimax robust estimator of the mean vector by iterative spectral dimension reduction
• Outlier-robust nonsmooth stochastic optimization
• Robust estimation for kernel exponential families with smoothed total variation distances

This page was built for publication: Robust estimators in high dimensions without the computational intractability

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6946432)