Near-Optimal Bounds for Learning Gaussian Halfspaces with Random Classification Noise

Authors: Ilias Diakonikolas, Jelena Diakonikolas, Daniel Kane, Puqian Wang, Nikos Zarifis

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

Reproducibility Variable Result LLM Response
Research Type Theoretical Our main contribution is a sample near-optimal efficient algorithm for this problem coupled with a matching statistical-computational tradeoff for SQ algorithms and low-degree polynomial tests.
Researcher Affiliation Academia Ilias Diakonikolas University of Wisconsin, Madison ilias@cs.wisc.edu Jelena Diakonikolas University of Wisconsin, Madison jelena@cs.wisc.edu Daniel M. Kane University of California, San Diego dakane@ucsd.edu Puqian Wang University of Wisconsin, Madison pwang333@wisc.edu Nikos Zarifis University of Wisconsin, Madison zarifis@wisc.edu
Pseudocode Yes Algorithm 1 Main Algorithm; Algorithm 2 Optimization; Algorithm 3 Main Algorithm; Algorithm 4 Initialization; Algorithm 5 Optimization; Algorithm 6 Testing Procedure
Open Source Code No The paper does not provide an explicit statement about the release of open-source code or a link to a code repository.
Open Datasets No The paper uses the 'standard Gaussian distribution' as a theoretical assumption for its problem setting, not a specific, publicly available dataset used for training. Therefore, no concrete access information to a public dataset is provided.
Dataset Splits No This is a theoretical paper and does not involve empirical experiments with real datasets. Therefore, no training/validation/test dataset splits are provided.
Hardware Specification No This is a theoretical paper and does not describe running experiments. Therefore, no hardware specifications are mentioned.
Software Dependencies No This is a theoretical paper and does not describe running experiments. Therefore, no software dependencies with specific version numbers are mentioned.
Experiment Setup No This is a theoretical paper and does not describe running empirical experiments. Therefore, no experimental setup details, hyperparameters, or training configurations are provided.