Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models
Authors: Gen Li, Yuting Wei, Yuxin Chen, Yuejie Chi
ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this work, we develop a suite of non-asymptotic theory towards understanding the data generation process of diffusion models in discrete time, assuming access to ℓ2-accurate estimates of the (Stein) score functions. [...] In contrast to prior works, our theory is developed based on an elementary yet versatile non-asymptotic approach without resorting to toolboxes for SDEs and ODEs. |
| Researcher Affiliation | Academia | Department of Statistics, The Chinese University of Hong Kong, Hong Kong. Department of Statistics and Data Science, Wharton School, University of Pennsylvania, Philadelphia, PA 19104, USA. Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA 19104, USA. Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA. |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statement about releasing open-source code or a link to a code repository for the methodology described. |
| Open Datasets | No | The paper discusses 'training data' in the context of diffusion models generally, but as a theoretical paper, it does not mention using or providing access information for a specific public dataset for experimental training. |
| Dataset Splits | No | The paper, being theoretical, does not discuss dataset splits for training, validation, or testing. |
| Hardware Specification | No | The paper is theoretical and focuses on mathematical proofs; thus, it does not mention any specific hardware used for experiments. |
| Software Dependencies | No | The paper is theoretical and does not mention any specific software dependencies with version numbers for reproducing experiments. |
| Experiment Setup | No | The paper is theoretical and does not describe any experimental setup details such as hyperparameters or training configurations. |