Multi-Class $H$-Consistency Bounds

Authors: Pranjal Awasthi, Anqi Mao, Mehryar Mohri, Yutao Zhong

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We present an extensive study of H-consistency bounds for multi-class classification. We give a series of new H-consistency bounds for surrogate multi-class losses, including max losses, sum losses, and constrained losses, both in the non-adversarial and adversarial cases, and for different differentiable or convex auxiliary functions used. We also prove that no non-trivial H-consistency bound can be given in some cases. Our proof techniques are also novel and likely to be useful in the analysis of other such guarantees.
Researcher Affiliation Collaboration Pranjal Awasthi Google Research New York, NY 10011 pranjalawasthi@google.com Anqi Mao Courant Institute New York, NY 10012 aqmao@cims.nyu.edu Mehryar Mohri Google Research & Courant Institute New York, NY 10011 mohri@google.com Yutao Zhong Courant Institute New York, NY 10012 yutao@cims.nyu.edu
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statements about releasing source code for the methodology or links to a code repository.
Open Datasets No The paper is theoretical and does not present any empirical studies or use datasets for training.
Dataset Splits No The paper is theoretical and does not involve data splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any hardware specifications used for running experiments.
Software Dependencies No The paper is theoretical and does not list any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe any experimental setup details such as hyperparameter values or training configurations.