Online A-Optimal Design and Active Linear Regression

Authors: Xavier Fontaine, Pierre Perrault, Michal Valko, Vianney Perchet

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

Reproducibility Variable Result LLM Response
Research Type Experimental Numerical experiments validate our theoretical findings.
Researcher Affiliation Collaboration 1Centre Borelli, ENS Paris-Saclay, Palaiseau, France 2Idemia, Courbevoie, France 3Google Deep Mind, Paris, France 4CREST, ENSAE, Palaiseau, France 5Criteo AI Lab, Paris, France.
Pseudocode Yes Algorithm 1 Naive randomized algorithm; Algorithm 2 Bandit algorithm
Open Source Code No The paper does not provide any statement or link indicating that the source code for their methods is publicly available.
Open Datasets No We run our experiments on synthetic data with horizon time T between 104 and 106, averaging the results over 25 rounds.
Dataset Splits No The paper mentions running experiments on synthetic data but does not specify any training, validation, or test dataset splits. The experimental process involves sequential sampling over rounds rather than predefined splits.
Hardware Specification No All the experiments ran in less than 15 minutes on a standard laptop.
Software Dependencies No The paper does not provide specific software dependencies with version numbers for reproducibility.
Experiment Setup No The paper describes the general setup of numerical simulations, including using synthetic data and averaging results over 25 rounds, but does not provide specific experimental setup details such as hyperparameters, model initialization, or optimizer settings.