Integral Probability Metrics PAC-Bayes Bounds

Authors: Ron Amit, Baruch Epstein, Shay Moran, Ron Meir

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

Reproducibility Variable Result LLM Response
Research Type Theoretical The entire paper is filled with mathematical definitions, theorems, lemmas, and proofs. No sections like 'Experiments', 'Results', 'Datasets', or 'Evaluation' are present. The abstract indicates a focus on generalizing PAC-Bayes bounds to IPMs, which is a theoretical contribution.
Researcher Affiliation Academia Pierre Alquier ENSAE - CREST, France; Alexandre Chrétien ENSAE - CREST, France
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any concrete access to source code for the methodology described, as it is a theoretical paper without an implemented methodology.
Open Datasets No The paper is theoretical and does not mention the use of any datasets, public or otherwise, for training or evaluation.
Dataset Splits No The paper is theoretical and does not discuss dataset splits (e.g., train/validation/test).
Hardware Specification No The paper is theoretical and does not mention any specific hardware 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 hyperparameters or training configurations.