量化扩散模型中的误差传播与模型崩溃
Quantifying Error Propagation and Model Collapse in Diffusion Models
AI总结：
本文理论分析了基于分数的扩散模型中递归训练导致模型崩溃的误差传播机制，给出了生成分布与目标分布之间累积散度的上下界，并刻画了不同漂移区域。
摘要：
机器学习模型越来越多地在合成数据上进行训练或微调。已观察到，在此类数据上递归训练会显著降低各种任务的性能，通常表现为逐渐偏离目标分布。在这项工作中，我们在基于分数的扩散模型设置下从理论上分析了这一现象。对于每个训练轮次使用合成数据与来自目标分布的新鲜样本组合的实际流程，我们获得了生成分布与目标分布之间累积散度的上界和下界。值得注意的是，据我们所知，这是首次对学习分布与目标分布之间的散度给出下界，即使对于标准扩散模型也是如此。我们的结果使我们能够根据分数估计误差和每代中使用的新鲜数据比例来表征不同的漂移区域。在某个区域中，多次再训练轮次后的累积散度可以表示为每代分数估计误差的折现和。我们还提供了合成数据和图像上的实证结果以说明该理论。
英文摘要：
Machine learning models are increasingly trained or fine-tuned on synthetic data. Recursively training on such data has been observed to significantly degrade performance in a wide range of tasks, often characterized by a progressive drift away from the target distribution. In this work, we theoretically analyze this phenomenon in the setting of score-based diffusion models. For a realistic pipeline where each training round uses a combination of synthetic data and fresh samples from the target distribution, we obtain upper and lower bounds on the accumulated divergence between the generated and target distributions. Notably, to the best of our knowledge, this is the first lower bound on the divergence between the learned and target distributions, even for standard diffusion models. Our results allow us to characterize different regimes of drift, depending on the score estimation error and the proportion of fresh data used in each generation. In a certain regime, the accumulated divergence after several retraining rounds can be expressed as a discounted sum of score estimation errors made at each generation. We also provide empirical results on synthetic data and images to illustrate the theory.
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。
