Training diffusion models typically relies on manually tuned noise schedules, which can waste computation on weakly informative noise regions and limit transfer across datasets, resolutions, and representations. We revisit noise schedule allocation through an information-theoretic lens and propose the conditional entropy rate of the forward process as a theoretically grounded, data-dependent diagnostic for identifying suboptimal noise-level allocation in existing schedules. Based on these insight, we introduce InfoNoise, a principled data-adaptive training noise schedule that replaces heuristic schedule design with an information-guided noise sampling distribution derived from entropy-reduction rates estimated from denoising losses already computed during training. Across natural-image benchmarks, InfoNoise matches or surpasses tuned EDM-style schedules, in some cases with a substantial training speedup (about $1.4\times$ on CIFAR-10). On discrete datasets, where standard image-tuned schedules exhibit significant mismatch, it reaches superior quality in up to $3\times$ fewer training steps. Overall, InfoNoise makes noise scheduling data-adaptive, reducing the need for per-dataset schedule design as diffusion models expand across domains.

翻译：扩散模型的训练通常依赖于手动调整的噪声调度方案，这类方案可能在信息量较弱的噪声区域浪费计算资源，并限制了模型在跨数据集、分辨率与表示形式间的迁移能力。本文从信息论视角重新审视噪声调度分配问题，提出以前向过程的条件熵率作为理论依据充分、数据依赖的诊断工具，用于识别现有调度方案中次优的噪声层级分配。基于该洞见，我们提出InfoNoise——一种基于原则的数据自适应训练噪声调度方法，它通过信息引导的噪声采样分布替代启发式调度设计，该分布源自训练过程中已计算的去噪损失所估计的熵减速率。在自然图像基准测试中，InfoNoise达到或超越了经调优的EDM风格调度方案的性能，部分情况下可实现显著的训练加速（在CIFAR-10上约$1.4\times$）。在离散数据集上，标准图像调优调度方案存在显著失配，而InfoNoise能以最多$3\times$更少的训练步数达到更优质量。总体而言，InfoNoise实现了噪声调度的数据自适应，随着扩散模型向多领域扩展，该方法降低了对逐数据集调度设计的需求。