Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

On Margin Maximization in Linear and ReLU Networks

Authors: Gal Vardi, Ohad Shamir, Nati Srebro

NeurIPS 2022 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper is purely theoretical in nature, and we do not see any potential negative societal impacts that should be discussed. (b) Did you include complete proofs of all theoretical results? [Yes]
Researcher Affiliation Academia Gal Vardi TTI-Chicago and Hebrew University EMAIL Ohad Shamir Weizmann Institute of Science EMAIL Nathan Srebro TTI-Chicago EMAIL
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper is theoretical and explicitly states 'N/A' for questions related to providing code for experimental results. There is no mention of releasing source code for the methodology described.
Open Datasets No The paper is purely theoretical and does not describe any empirical studies involving training on datasets.
Dataset Splits No The paper is theoretical and does not involve empirical experiments, thus no dataset split information for validation is provided.
Hardware Specification No The paper is purely theoretical and does not describe any hardware used for experiments.
Software Dependencies No The paper is purely theoretical and does not mention specific ancillary software or their version numbers.
Experiment Setup No The paper is purely theoretical and does not describe any experimental setup details such as hyperparameters or training configurations.