Weston-Watkins Hinge Loss and Ordered Partitions
Authors: Yutong Wang, Clayton Scott
NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this work we introduce a novel discrete loss function for multiclass classification, the ordered partition loss, and prove that the WW-hinge loss is calibrated with respect to this loss. We also argue that the ordered partition loss is minimally emblematic among discrete losses satisfying this property. Finally, we apply our theory to justify the empirical observation made by Doˇgan et al. [1] that the WW-SVM can work well even under massive label noise, a challenging setting for multiclass SVMs. |
| Researcher Affiliation | Academia | Yutong Wang University of Michigan yutongw@umich.edu Clayton D. Scott University of Michigan clayscot@umich.edu |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not include any statements or links indicating that open-source code for the described methodology is provided. |
| Open Datasets | No | The paper is theoretical and does not use or reference any specific public datasets for training purposes. It discusses general concepts like 'training samples' but not concrete datasets. |
| Dataset Splits | No | The paper is theoretical and does not describe specific dataset splits (training, validation, test) for experimental reproduction. |
| Hardware Specification | No | The paper is theoretical and does not describe any specific hardware used for computations or experiments. The mention of 'computer search' in relation to the minimally emblematic loss is a computational verification of a theoretical property, not an experiment requiring detailed hardware specifications. |
| Software Dependencies | No | The paper does not list any specific software dependencies with version numbers. |
| Experiment Setup | No | The paper is theoretical and does not include details about an experimental setup, such as hyperparameter values, training configurations, or system-level settings. |