paper-with-me

홈 › Papers

Flow matching achieves almost minimax optimal convergence

2024-05-31 · Kenji Fukumizu, Taiji Suzuki, Noboru Isobe, Kazusato Oko, Masanori Koyama

Flow matching (FM) has gained significant attention as a simulation-free generative model. Unlike diffusion models, which are based on stochastic differential equations, FM employs a simpler approach by solving an ordinary differential equation with an initial condition from a normal distribution, thus streamlining the sample generation process. This paper discusses the convergence properties of FM for large sample size under the $p$-Wasserstein distance, a measure of distributional discrepancy. We establish that FM can achieve an almost minimax optimal convergence rate for $1 \leq p \leq 2$, 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.

📄 PDF Abstract BibTeX arXiv:2405.20879

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

On the minimax optimality of Flow Matching through the connection to kernel density estimation

2025-04-17 · Lea Kunkel, Mathias Trabs

Flow Matching has recently gained attention in generative modeling as a simple and flexible alternative to diffusion models, the current state of the art. While existing statistical guarantees adapt tools from the analys…

Density Estimation

On Flow Matching KL Divergence

2025-11-07 · Maojiang Su, Jerry Yao-Chieh Hu, Sophia Pi, Han Liu arxiv

We derive a deterministic, non-asymptotic upper bound on the Kullback-Leibler (KL) divergence of the flow-matching distribution approximation. In particular, if the $L_2$ flow-matching loss is bounded by $ε^2 > 0$, then …

Multinomial Logit Bandit with Low Switching Cost

2020-07-09 · ICML 2020 1 · Kefan Dong, Yingkai Li, Qin Zhang, Yuan Zhou

We study multinomial logit bandit with limited adaptivity, where the algorithms change their exploration actions as infrequently as possible when achieving almost optimal minimax regret. We propose two measures of adapti…

Approximation and Parameterized Complexity of Minimax Approval Voting

2016-07-26 · Marek Cygan, Łukasz Kowalik, Arkadiusz Socała, Krzysztof Sornat

We present three results on the complexity of Minimax Approval Voting. First, we study Minimax Approval Voting parameterized by the Hamming distance $d$ from the solution to the votes. We show Minimax Approval Voting adm…

Minimax Optimality of Classical Scaling Under General Noise Conditions

2025-02-02 · Siddharth Vishwanath, Ery Arias-Castro

We establish the consistency of classical scaling under a broad class of noise models, encompassing many commonly studied cases in literature. Our approach requires only finite fourth moments of the noise, significantly …