Linear regression without correspondence

Authors: Daniel J. Hsu, Kevin Shi, Xiaorui Sun

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Our algorithms are not meant for practical deployment, but instead are intended to shed light on the computational difficulty of the least squares problem and the average-case recovery problem.
Researcher Affiliation Collaboration Daniel Hsu Columbia University New York, NY djhsu@cs.columbia.edu Kevin Shi Columbia University New York, NY kshi@cs.columbia.edu Xiaorui Sun Microsoft Research Redmond, WA xiaoruisun@cs.columbia.edu
Pseudocode Yes Algorithm 1 Approximation algorithm for least squares problem
Open Source Code No The paper states: 'Our algorithms are not meant for practical deployment, but instead are intended to shed light on the computational difficulty of the least squares problem and the average-case recovery problem.' There is no mention or link to open-source code for the described methodology.
Open Datasets No The paper describes theoretical models using i.i.d. draws from distributions (e.g., N(0, Id)) rather than using or referring to specific named public datasets for training.
Dataset Splits No The paper is theoretical and does not conduct empirical experiments, therefore it does not provide details on dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and discusses algorithmic properties and statistical bounds, without reporting empirical experiments. Therefore, no hardware specifications are mentioned.
Software Dependencies No The paper focuses on theoretical analysis and algorithm design. It does not describe empirical implementations or list any specific software dependencies with version numbers required for replication.
Experiment Setup No The paper is theoretical, presenting algorithms and statistical bounds. It does not detail an experimental setup with specific hyperparameter values or training configurations for empirical evaluation.