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.
Exponential Convergence Guarantees for Iterative Markovian Fitting
Authors: Marta Gentiloni Silveri, Giovanni Conforti, Alain Durmus
NeurIPS 2025 | Venue PDF | LLM Run Details | Input Tokens: 30,379 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 2,074 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 | Our analysis is purely theoretical and does not account for the mimicking drift estimation error or the discretization error arising in practical implementations. These limitations point to natural directions for future work, particularly the extension to finite-time settings and the inclusion of approximation errors in the theoretical analysis. ... Since this work is of theoretical nature, we do not provide experimental data, hence our answer. |
| Researcher Affiliation | Academia | Marta Gentiloni Silveri École polytechnique Route de Saclay, 91120 Palaiseau, France EMAIL Giovanni Conforti Università degli Studi di Padova Via Trieste, 63, 35131 Padova, Italia EMAIL Alain Durmus École polytechnique Route de Saclay, 91120 Palaiseau, France EMAIL |
| Pseudocode | Yes | Algorithm 1: Iterative Markovian Fitting ... Algorithm 2: Iterative Markovian Fitting (Geometric Interpretation) ... Algorithm 3: Diffusion Schrödinger Bridge Matching |
| Open Source Code | No | Since this work is of theoretical nature, we do not provide experimental data, hence our answer. |
| Open Datasets | No | Since this work is of theoretical nature, we do not provide experimental data, hence our answer. |
| Dataset Splits | No | Since this work is of theoretical nature, we do not provide experimental data, hence our answer. |
| Hardware Specification | No | Since this work is of theoretical nature, we do not provide experimental data, hence our answer. |
| Software Dependencies | No | Since this work is of theoretical nature, we do not provide experimental data, hence our answer. |
| Experiment Setup | No | Since this work is of theoretical nature, we do not provide experimental data, hence our answer. |