Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
On Certified Generalization in Structured Prediction
Authors: Bastian Boll, Christoph Schnörr
NeurIPS 2023 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We present a novel PAC-Bayesian risk bound for structured prediction wherein the rate of generalization scales not only with the number of structured examples but also with their size. ... Accordingly, we do not present any empirical results on real-world data. |
| Researcher Affiliation | Academia | Bastian Boll Image & Pattern Analysis Group Heidelberg University EMAIL Christoph Schnörr Image & Pattern Analysis Group Heidelberg University EMAIL |
| Pseudocode | No | The paper contains mathematical derivations and theorems but no explicitly labeled algorithm blocks or pseudocode. |
| Open Source Code | No | The paper does not contain any explicit statements about releasing source code or links to a code repository for the methodology described. |
| Open Datasets | No | The paper states: 'Accordingly, we do not present any empirical results on real-world data.' The 'Numerical Toy Example' uses a synthetic 'uniform reference measure ν2 on the unit cube [0, 1]2' which is not a publicly available dataset. |
| Dataset Splits | No | The paper does not report empirical experiments on real-world data, and therefore does not provide details on training, validation, or test dataset splits. |
| Hardware Specification | No | The paper is theoretical and does not mention any specific hardware used for computations. |
| Software Dependencies | No | The paper is theoretical and does not mention specific software dependencies with version numbers. |
| Experiment Setup | No | The paper does not present empirical results on real-world data and therefore does not provide specific experimental setup details such as hyperparameters or training configurations. |