The Geometry of Mixability
Authors: Armando J Cabrera Pacheco, Robert Williamson
TMLR 2023 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | The main goal of this work is to provide such geometric interpretation. The motivation stems from an observation made by Vovk (2015): a η-mixable loss can be characterized as the positiveness of the infimum of the quotient of the curvatures of the a strictly proper loss function ℓand the log loss ℓlog for binary outcomes. Here as usual, loss functions are defined on the 2-simplex 2 (see (1.1)). Moreover, he then proves that fundamentality (see Vovk (Vovk, 2015)) of a loss can be characterized as the finiteness of the supremum of the same quotient of curvatures. These two results suggest that these properties are geometric, meaning that they can be studied using differential geometry tools, and in this regard, mixability and fundamentality should not depend on the coordinates chosen to express them. [...] This work should be considered as complementing the understanding of mixable loss functions and providing a new geometric insight into them. |
| Researcher Affiliation | Academia | Armando J. Cabrera Pacheco EMAIL University of Tübingen and Tübingen AI Center, Germany Robert C. Williamson EMAIL University of Tübingen and Tübingen AI Center, Germany |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. It is a theoretical paper focusing on mathematical characterizations and proofs. |
| Open Source Code | No | The paper does not provide any concrete access to source code for the methodology described. There is no mention of code release, repository links, or code in supplementary materials. |
| Open Datasets | No | The paper is theoretical and does not present any empirical studies or experiments that would require specific datasets. Therefore, no information about publicly available or open datasets is provided. |
| Dataset Splits | No | The paper is theoretical and does not describe any experiments that would involve dataset splits. Therefore, no information on training, testing, or validation splits is provided. |
| Hardware Specification | No | The paper is purely theoretical and does not describe any computational experiments or their execution. Therefore, no hardware specifications are mentioned. |
| Software Dependencies | No | The paper is theoretical and does not detail any software implementations or dependencies with version numbers for experimental reproducibility. |
| Experiment Setup | No | The paper is theoretical and does not include any experimental setup details such as hyperparameters, training configurations, or system-level settings, as no experiments are conducted. |