On the Error Resistance of Hinge-Loss Minimization

Authors: Kunal Talwar

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical we identify a set of conditions on the data under which such surrogate loss minimization algorithms provably learn the correct classifier. This allows us to establish, in a unified framework, the robustness of these algorithms under various models on data as well as error.Our proof relates the optimality conditions to the 0-1 loss of the resulting classifier.
Researcher Affiliation Industry Kunal Talwar Apple Cupertino, CA 95014 ktalwar@apple.com Work performed while at Google Brain.
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets No The paper focuses on theoretical analysis of data distributions and samples, and does not mention or provide access information for any specific publicly available training dataset.
Dataset Splits No The paper is theoretical and does not conduct empirical experiments, therefore no specific training, validation, or test dataset splits are provided.
Hardware Specification No The paper is theoretical and does not describe running experiments, therefore no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not describe running experiments, therefore no software dependencies with version numbers are provided.
Experiment Setup No The paper is theoretical and does not describe running experiments, therefore no specific experimental setup details such as hyperparameters are provided.