Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time Complexity

Authors: Haoxuan Chen, Yinuo Ren, Lexing Ying, Grant Rotskoff

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical As a theoretical paper, we do not include experiments.
Researcher Affiliation Academia Haoxuan Chen ICME Stanford University haoxuanc@stanford.edu; Yinuo Ren ICME Stanford University yinuoren@stanford.edu; Lexing Ying Department of Mathematics and ICME Stanford University lexing@stanford.edu; Grant M. Rotskoff Department of Chemistry and ICME Stanford University rotskoff@stanford.edu
Pseudocode Yes Algorithm 1: PIADM-SDE; Algorithm 2: PIADM-ODE
Open Source Code No As a theoretical paper, we do not include experiments.
Open Datasets No As a theoretical paper, we do not include experiments.
Dataset Splits No As a theoretical paper, we do not include experiments.
Hardware Specification No The paper is theoretical and does not describe specific hardware used for its own research or experiments.
Software Dependencies No The paper is theoretical and does not describe specific software dependencies with version numbers for experimental reproducibility.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with hyperparameters or training configurations.