Online Active Regression

Authors: Cheng Chen, Yi Li, Yiming Sun

ICML 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The numerical results verify our theoretical results and show that our methods have comparable performance with offline active regression algorithms.
Researcher Affiliation Academia 1School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore.
Pseudocode Yes Algorithm 1 Online Active Regression for p (1, 2)
Open Source Code No The paper does not include an unambiguous statement or link to the open-source code for the described methodology.
Open Datasets Yes We evaluate our algorithm on a realworld dataset, the gas sensor data (Vergara et al., 2012; Rodriguez-Lujan et al., 2014) from the UCI Machine Learning Repository1.
Dataset Splits No The paper mentions varying budget sizes for label queries and running independent trials, but it does not specify explicit training, validation, or test dataset splits in a conventional supervised learning sense.
Hardware Specification Yes All our experiments are conducted in MATLAB on a Macbook Pro with an i5 2.9GHz CPU and 8GB of memory.
Software Dependencies No The paper states that experiments were conducted in MATLAB but does not provide a specific version number for MATLAB or any other software dependencies with versions.
Experiment Setup Yes We vary the budget sizes for the synthetic data between 800 and 1400 (8% 14% of the data size) and for the realworld data between 1600 and 2500 (12% 18% of the data size). For each budget size, we run 20 independent trials and calculate the mean relative error and standard deviation.