A Category-theoretical Meta-analysis of Definitions of Disentanglement
Authors: Yivan Zhang, Masashi Sugiyama
ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Although large-scale experimental studies exist (Locatello et al., 2019), theoretical analyses and systematic comparisons are limited (Sepliarskaia et al., 2019; Carbonneau et al., 2022). It is worth clarifying that this paper does not discuss metrics, models, methods, supervision, and learnability. |
| Researcher Affiliation | Academia | 1The University of Tokyo, Tokyo, Japan 2RIKEN AIP, Tokyo, Japan. |
| Pseudocode | No | The paper contains mathematical definitions, propositions, theorems, and various diagrams (commutative diagrams and string diagrams) but does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper explicitly states, "It is worth clarifying that this paper does not discuss metrics, models, methods, supervision, and learnability." As it's a theoretical meta-analysis and does not propose a new implementable method, there is no source code for its own methodology to be provided. |
| Open Datasets | No | The paper is a theoretical meta-analysis and does not involve conducting experiments or training models on datasets. Thus, it does not specify any dataset for training. |
| Dataset Splits | No | The paper is a theoretical meta-analysis and does not involve conducting experiments or data splits for validation. No information on dataset splits (train/validation/test) is provided. |
| Hardware Specification | No | The paper is a theoretical work and does not describe any computational experiments. Therefore, no hardware specifications for running experiments are provided. |
| Software Dependencies | No | The paper is a theoretical work and does not describe any computational experiments. Therefore, no specific software dependencies with version numbers are provided. |
| Experiment Setup | No | The paper is a theoretical work and does not describe any experiments, models, or training procedures. Therefore, no experimental setup details such as hyperparameters or training settings are provided. |