Notice: 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. Full accuracy metrics and methodology are described in [1].

Flow matching achieves almost minimax optimal convergence

Authors: Kenji Fukumizu, Taiji Suzuki, Noboru Isobe, Kazusato Oko, Masanori Koyama

ICLR 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper discusses the convergence properties of FM for large sample size under the p-Wasserstein distance. We establish that FM can achieve an almost minimax optimal convergence rate for 1 p 2, presenting the first theoretical evidence that FM can reach convergence rates comparable to those of diffusion models. Our analysis extends existing frameworks by examining a broader class of mean and variance functions for the vector fields and identifies specific conditions necessary to attain almost optimal rates. 4 THEORETICAL DETAILS
Researcher Affiliation Collaboration Kenji Fukumizu The Institute of Statistical Mathematics/Preferred Networks Tokyo, Japan EMAIL Taiji Suzuki University of Tokyo/RIKEN AIP Tokyo, Japan EMAIL Masanori Koyama Preferred Networks/University of Tokyo Tokyo, Japan EMAIL
Pseudocode No The paper contains detailed mathematical proofs and theoretical analyses but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any explicit statements about releasing source code, nor does it provide links to code repositories or mention code in supplementary materials.
Open Datasets No The paper is theoretical and analyzes convergence rates for a generic setting where 'n training data {x(i)}n i=1 is i.i.d. samples from P[1]'. It does not refer to any specific publicly available datasets or provide access information for any data.
Dataset Splits No The paper focuses on theoretical analysis and does not conduct experiments requiring dataset splits. Therefore, no information about training, testing, or validation splits is provided.
Hardware Specification No The paper is a theoretical work and does not describe any experimental setups or computational hardware used.
Software Dependencies No As a theoretical paper, there is no mention of specific software dependencies or their version numbers.
Experiment Setup No The paper is purely theoretical, focusing on mathematical convergence rates, and therefore does not include details on experimental setup, hyperparameters, or training configurations.