Consistent regression when oblivious outliers overwhelm

Authors: Tommaso D’Orsi, Gleb Novikov, David Steurer

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We show that consistent estimation is possible with nearly linear sample size and inverse-polynomial inlier fraction. Concretely, we show that the Huber loss estimator is consistent for every sample size n = ω(d/α2) and achieves an error rate of O(d/α2n)1/2 (both bounds are optimal up to constant factors). Our results extend to designs far beyond the Gaussian case and only require the column span of X to not contain approximately sparse vectors...
Researcher Affiliation Academia 1Department of Computer Science, ETH Z urich, Switzerland.
Pseudocode Yes Algorithm 1 Multivariate linear regression iteration via median
Open Source Code No The paper does not provide any concrete access to source code for the methodology described.
Open Datasets No The paper is theoretical and does not report on experiments conducted using datasets. Therefore, no information about public datasets is provided.
Dataset Splits No The paper is theoretical and does not report on empirical experiments with data. Thus, there is no information about training, validation, or test splits.
Hardware Specification No The paper is theoretical and does not describe any experiments that would require hardware. Therefore, no hardware specifications are provided.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not detail any experimental setup, hyperparameters, or system-level training settings.