Robust Mean Estimation Without Moments for Symmetric Distributions

Authors: Gleb Novikov, David Steurer, Stefan Tiegel

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We study the problem of robustly estimating the mean or location parameter without moment assumptions. Known computationally efficient algorithms rely on strong distributional assumptions, such as sub-Gaussianity, or (certifiably) bounded moments. Moreover, the guarantees that they achieve in the heavy-tailed setting are weaker than those for sub-Gaussian distributions with known covariance. In this work, we show that such a tradeoff, between error guarantees and heavy-tails, is not necessary for symmetric distributions. We show that for a large class of symmetric distributions, the same error as in the Gaussian setting can be achieved efficiently.
Researcher Affiliation Academia Gleb Novikov Department of Computer Science ETH Zurich David Steurer Department of Computer Science ETH Zurich Stefan Tiegel Department of Computer Science ETH Zurich
Pseudocode Yes Algorithm D.3 (Filtering Algorithm). Input: ε-corrupted sample y1, . . . , yn and σ > 0. Output: Location estimate ˆµ. [...] Algorithm E.4 (Filtering Algorithm). Input: ε-corrupted sample y1, . . . , yn and σ > 0. Output: Location estimate ˆµ.
Open Source Code No The paper does not contain any explicit statements or links indicating that the source code for the described methodology is publicly available.
Open Datasets No The paper is theoretical and does not conduct empirical studies involving datasets or training. No information about dataset availability or access is provided.
Dataset Splits No The paper is theoretical and does not conduct empirical studies. It does not mention any dataset splits (training, validation, or testing).
Hardware Specification No The paper is theoretical and does not report on experiments. Therefore, no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not report on experiments. It does not list any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup, hyperparameters, or training configurations.