Revenue maximization via machine learning with noisy data

Authors: Ellen Vitercik, Tom Yan

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We provide guarantees when arbitrarily correlated noise is added to the training set; we only require that the noise has bounded magnitude or is sub-Gaussian. Our main contribution is a sensitivity analysis of revenue with respect to the noise s magnitude.
Researcher Affiliation Academia Ellen Vitercik Department of Electrical Engineering and Computer Sciences University of California, Berkeley vitercik@berkeley.edu Tom Yan Department of Machine Learning Carnegie Mellon University tyyan@cmu.edu
Pseudocode No The paper presents mathematical definitions, theorems, lemmas, and proofs, but does not include pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any specific links to source code, nor does it state that code is available in supplementary materials or upon request. The checklist explicitly states N/A for code for reproducing experimental results.
Open Datasets No The paper states 'A major bottleneck for empirical evaluations in learningbased mechanism design is the lack of public datasets we are only aware of one, from e Bay [44]' but does not provide access information for any dataset used for its analysis, which is primarily theoretical.
Dataset Splits No The paper is theoretical and does not report experimental results that would require data partitioning into training, validation, and test sets. Therefore, no specific dataset split information is provided.
Hardware Specification No The paper is theoretical and does not describe any experiments that would require specific hardware. Therefore, no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not describe any experimental setup that would require specific software dependencies. Therefore, no software details with version numbers are mentioned.
Experiment Setup No The paper is theoretical and does not report experimental results, thus no specific experimental setup details such as hyperparameters or training configurations are provided.