arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.07032stat.MLcs.LG
收藏

从最优得分匹配到最优采样

From optimal score matching to optimal sampling

Yale University(耶鲁大学);University of Chicago(芝加哥大学)

Zehao Dou, Subhodh Kotekal, Zhehao Xu, Harrison H. Zhou

AI总结:

该研究针对基于得分的扩散模型的得分估计最优统计速率问题,推导了光滑紧支撑密度下得分估计的精确极小极大速率,证明扩散模型生成样本分布可达无对数项、无需提前停止的最优密度估计速率。

摘要:

近期高保真图像、音频和视频算法生成领域取得的显著进展,很大程度上得益于基于得分的扩散模型的巨大成功。其中一个关键实现步骤是得分匹配,即从训练数据中估计前向扩散过程的得分函数。已有文献表明,经训练的扩散模型生成样本的分布与真实分布之间的总变分距离,可由得分匹配风险控制。\n尽管基于得分的扩散模型已得到广泛应用,但关于得分估计的精确最优统计速率及其在密度估计中应用的基础理论问题仍未解决。我们针对具有紧支撑的光滑密度,建立了得分估计的精确极小极大速率。具体而言,给定支撑集为[-1,1]的未知α-赫尔德密度f的n个独立同分布样本,我们证明了对于所有α>0且t≥0的情况,在得分匹配损失下,估计扩散后分布f*N(0,t)的得分函数的极小极大速率为1/(nt²) ∧ 1/(nt^(3/2)) ∧ (t^(α-1) + n^(-2(α-1)/(2α+1)))。由此可得,扩散模型生成样本的分布f̂达到了精确极小极大速率E(dTV(f̂,f)²) ≲ n^(-2α/(2α+1)),且对于所有α>0均成立,该结果既没有文献中常见的额外对数项,据我们所知,也无需现有所有方法都要求的提前停止操作。

英文摘要:

The recent, impressive advances in algorithmic generation of high-fidelity image, audio, and video are largely due to great successes in score-based diffusion models. A key implementing step is score matching, that is, the estimation of the score function of the forward diffusion process from training data. As shown in earlier literature, the total variation distance between the law of a sample generated from the trained diffusion model and the ground truth distribution can be controlled by the score matching risk. Despite the widespread use of score-based diffusion models, basic theoretical questions concerning exact optimal statistical rates for score estimation and its application to density estimation remain open. We establish the sharp minimax rate of score estimation for smooth, compactly supported densities. Formally, given \(n\) i.i.d. samples from an unknown \(α\)-Hölder density \(f\) supported on \([-1, 1]\), we prove the minimax rate of estimating the score function of the diffused distribution \(f * \mathcal{N}(0, t)\) with respect to the score matching loss is \(\frac{1}{nt^2} \wedge \frac{1}{nt^{3/2}} \wedge (t^{α-1} + n^{-2(α-1)/(2α+1)})\) for all \(α> 0\) and \(t \ge 0\). As a consequence, it is shown the law \(\hat{f}\) of a sample generated from the diffusion model achieves the sharp minimax rate \(\bE(\dTV(\hat{f}, f)^2) \lesssim n^{-2α/(2α+1)}\) for all \(α> 0\) without any extraneous logarithmic terms which are prevalent in the literature, and without the need for early stopping which has been required for all existing procedures to the best of our knowledge.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑