Streaming Algorithms for High-Dimensional Robust Statistics

Authors: Ilias Diakonikolas, Daniel M. Kane, Ankit Pensia, Thanasis Pittas

ICML 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Our computationally efficient algorithm makes a single pass over the data, uses near-optimal space, and matches the error guarantees of previous polynomial-time algorithms for the problem. As a corollary, we obtain streaming algorithms with near-optimal space complexity for several more complex tasks, including robust covariance estimation, robust regression, and more generally robust stochastic optimization.
Researcher Affiliation Academia 1University of Wisconsin-Madison 2University of California, San Diego.
Pseudocode Yes Algorithm 1 Robust Mean Estimation in polylog iterations and Algorithm 5 Robust Mean Estimation In Single-Pass Streaming Model
Open Source Code No No statement or link indicating open-source code for the described methodology.
Open Datasets No The paper focuses on theoretical algorithm design and analysis, and does not involve empirical evaluation on publicly available datasets for training purposes.
Dataset Splits No The paper is theoretical and does not describe experimental validation or dataset splits.
Hardware Specification No The paper describes theoretical algorithms and does not report on experiments requiring specific hardware specifications.
Software Dependencies No The paper describes theoretical algorithms and does not report on experiments requiring specific software dependencies with version numbers.
Experiment Setup No The paper describes theoretical algorithms and does not report on experiments with a specific experimental setup, including hyperparameters or training configurations.