Second-Order Uncertainty Quantification: A Distance-Based Approach
Authors: Yusuf Sale, Viktor Bengs, Michele Caprio, Eyke Hüllermeier
ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Although the focus of our work is on the theoretical aspects of uncertainty measures, a systematic experimental comparison in the context of evidential deep learning would be intriguing. |
| Researcher Affiliation | Academia | 1Institute of Informatics, LMU Munich, Munich, Germany 2Munich Center for Machine Learning, Munich, Germany 3Precise Center, University of Pennsylvania, Philadelphia, USA. |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. Its content is primarily theoretical with mathematical derivations and proofs. |
| Open Source Code | Yes | The code to replicate our numerical results is available in a public repository (https://github.com/YSale/uq-distance). |
| Open Datasets | No | The paper focuses on theoretical analysis and uses illustrative examples with specific distributions (e.g., Dirichlet, Bernoulli) rather than conducting experiments on named, publicly available datasets with specified access information. |
| Dataset Splits | No | The paper does not provide specific training/test/validation dataset splits. Its focus is theoretical analysis with numerical illustrations, not empirical validation on datasets. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run its numerical examples or computations. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers for its computational aspects. |
| Experiment Setup | No | The paper focuses on theoretical definitions and proofs, and while it discusses computational aspects of its proposed measures, it does not provide concrete experimental setup details such as hyperparameters, model initialization, or specific training configurations typical of empirical studies. |