$\ell_1$-regression with Heavy-tailed Distributions

Authors: Lijun Zhang, Zhi-Hua Zhou

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper focuses on the statistical property of (6), and we leave the design of efficient optimization procedures as a future work.
Researcher Affiliation Academia Lijun Zhang, Zhi-Hua Zhou National Key Laboratory for Novel Software Technology Nanjing University, Nanjing 210023, China {zhanglj, zhouzh}@lamda.nju.edu.cn
Pseudocode No No. The paper primarily focuses on theoretical analysis and proofs, stating 'This paper focuses on the statistical property of (6), and we leave the design of efficient optimization procedures as a future work.' No pseudocode or algorithm blocks are provided.
Open Source Code No No. The paper states 'We will provide detailed investigations in an extended paper.' and 'we leave the design of efficient optimization procedures as a future work.' There is no concrete access to source code provided.
Open Datasets No No. The paper is theoretical and discusses 'input-output pairs that are independently drawn from an unknown distribution P' for its analysis, but it does not mention or provide access information for any specific public dataset.
Dataset Splits No No. As a theoretical paper without empirical experiments, it does not specify any dataset split information for training, validation, or testing.
Hardware Specification No No. As a theoretical paper, it does not describe any experimental hardware specifications.
Software Dependencies No No. As a theoretical paper, it does not specify any software dependencies with version numbers.
Experiment Setup No No. The paper is theoretical and states, 'This paper focuses on the statistical property of (6), and we leave the design of efficient optimization procedures as a future work.' Consequently, no specific experimental setup details or hyperparameters are provided.