Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
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.
The Pessimistic Limits and Possibilities of Margin-based Losses in Semi-supervised Learning
Authors: Jesse Krijthe, Marco Loog
NeurIPS 2018 | Venue PDF | LLM Run Details | Input Tokens: 15,359 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 3,748 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | The main conclusion from our analysis (Theorems 1 and 2) is that for classifiers defined by convex margin-based surrogate losses that are decreasing, it is impossible to come up with any semi-supervised approach that is able to guarantee safe improvement. |
| Researcher Affiliation | Academia | Jesse H. Krijthe Radboud University, The Netherlands Marco Loog Delft University of Technology, The Netherlands University of Copenhagen, Denmark |
| Pseudocode | No | The paper contains mathematical formulations and proofs but no structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any concrete access information for source code related to its methodology. |
| Open Datasets | No | The paper is theoretical and does not mention specific datasets used for training or empirical evaluation within its own work. |
| Dataset Splits | No | The paper is theoretical and does not describe any dataset splits (train/validation/test) for empirical evaluation. |
| Hardware Specification | No | The paper is theoretical and does not mention any specific hardware used for experiments. |
| Software Dependencies | No | The paper is theoretical and does not specify any 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. |