List-Decodable Mean Estimation in Nearly-PCA Time

Authors: Ilias Diakonikolas, Daniel Kane, Daniel Kongsgaard, Jerry Li, Kevin Tian

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

Reproducibility Variable Result LLM Response
Research Type Theoretical Our main result is a new algorithm for bounded covariance distributions with optimal sample complexity and near-optimal error guarantee, running in nearly-PCA time. and This work does not present any direct foreseeable societal consequence, as it is a result primarily of theoretical interest to the community.
Researcher Affiliation Collaboration Ilias Diakonikolas Department of Computer Science University of Wisconsin, Madison Madison, WI 53706 ilias@cs.wisc.edu; Daniel M. Kane Department of Computer Science University of California, San Diego La Jolla, CA 92093 dakane@cs.ucsd.edu; Daniel Kongsgaard Department of Mathematics University of California, San Diego La Jolla, CA 92093 dkongsga@ucsd.edu; Jerry Li Microsoft Research Redmond, WA 98052 jerrl@microsoft.com; Kevin Tian Department of Computer Science Stanford University Stanford, CA 94305 kjtian@stanford.edu
Pseudocode Yes Algorithm 1 SIFT(T, δ)
Open Source Code No The paper states 'Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A]' and does not provide any links or statements about open-source code availability.
Open Datasets No The paper does not mention any specific publicly available or open datasets used for training or evaluation, nor does it provide access information.
Dataset Splits No The paper is theoretical and does not describe any experiments with data, thus it does not provide specific dataset split information for validation.
Hardware Specification No The paper is theoretical and states 'Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [N/A]', indicating no specific hardware details are provided.
Software Dependencies No The paper is theoretical and does not describe any experiments, thus it does not provide specific ancillary software details with version numbers.
Experiment Setup No The paper is theoretical and does not describe any experiments, thus it does not provide specific experimental setup details like hyperparameters or training configurations.