Information-Guided Noise Allocation for Efficient Diffusion Training

• URL: http://arxiv.org/abs/2602.18647v1
• Date: Fri, 20 Feb 2026 22:45:01 GMT
• Title: Information-Guided Noise Allocation for Efficient Diffusion Training
• Authors: Gabriel Raya, Bac Nguyen, Georgios Batzolis, Yuhta Takida, Dejan Stancevic, Naoki Murata, Chieh-Hsin Lai, Yuki Mitsufuji, Luca Ambrogioni,
• Abstract summary: InfoNoise is a principled data-adaptive training noise schedule that replaces schedule design with an information-guided noise sampling distribution.<n>Across natural-image benchmarks, InfoNoise matches or surpasses tuned EDM-style schedules, in some cases with a substantial training speedup.<n>Overall, InfoNoise makes noise scheduling data-adaptive, reducing the need for per-dataset schedule design as diffusion models expand across domains.
• Score: 50.49440376762109
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Beyond Fixed Horizons: A Theoretical Framework for Adaptive Denoising Diffusions [1.9116784879310031]
  We introduce a new class of generative diffusion models that achieve a time-homogeneous structure for both the noising and denoising processes.<n>A key feature of the model is its adaptability to the target data, enabling a variety of downstream tasks using a pre-trained unconditional generative model.
  arXiv  Detail & Related papers  (2025-01-31T18:23:27Z)
• Score-Optimal Diffusion Schedules [29.062842062257918]
  An appropriate discretisation schedule is crucial to obtain high quality samples.<n>This paper presents a novel algorithm for adaptively selecting an optimal discretisation schedule.<n>We find that our learned schedule recovers performant schedules previously only discovered through manual search.
  arXiv  Detail & Related papers  (2024-12-10T19:26:51Z)
• Constant Rate Scheduling: Constant-Rate Distributional Change for Efficient Training and Sampling in Diffusion Models [16.863038973001483]
  We propose a general approach to optimize noise schedules for training and sampling in diffusion models.<n>We evaluate the effectiveness of our approach on unconditional and class-conditional image-generation tasks.<n>By using our approach for optimizing both training and sampling schedules, we achieved a state-of-the-art FID score of 2.03.
  arXiv  Detail & Related papers  (2024-11-19T03:02:39Z)
• ANT: Adaptive Noise Schedule for Time Series Diffusion Models [5.752266579415516]
  We propose Adaptive Noise schedule for Time series diffusion models (ANT) It automatically predetermines proper noise schedules for given TS datasets based on their statistics representing non-stationarity. We validate our method across various tasks, including TS forecasting, refinement, and generation, on datasets from diverse domains.
  arXiv  Detail & Related papers  (2024-10-18T14:16:54Z)
• Improved Noise Schedule for Diffusion Training [51.849746576387375]
  We propose a novel approach to design the noise schedule for enhancing the training of diffusion models.<n>We empirically demonstrate the superiority of our noise schedule over the standard cosine schedule.
  arXiv  Detail & Related papers  (2024-07-03T17:34:55Z)
• Impact of Noisy Supervision in Foundation Model Learning [91.56591923244943]
  This paper is the first work to comprehensively understand and analyze the nature of noise in pre-training datasets.<n>We propose a tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization.
  arXiv  Detail & Related papers  (2024-03-11T16:22:41Z)
• Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks [91.15120211190519]
  This paper aims to understand the nature of noise in pre-training datasets and to mitigate its impact on downstream tasks. We propose a light-weight black-box tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise.
  arXiv  Detail & Related papers  (2023-09-29T06:18:15Z)
• NLIP: Noise-robust Language-Image Pre-training [95.13287735264937]
  We propose a principled Noise-robust Language-Image Pre-training framework (NLIP) to stabilize pre-training via two schemes: noise-harmonization and noise-completion. Our NLIP can alleviate the common noise effects during image-text pre-training in a more efficient way.
  arXiv  Detail & Related papers  (2022-12-14T08:19:30Z)
• Perception Prioritized Training of Diffusion Models [34.674477039333475]
  We show that restoring data corrupted with certain noise levels offers a proper pretext for the model to learn rich visual concepts. We propose to prioritize such noise levels over other levels during training, by redesigning the weighting scheme of the objective function.
  arXiv  Detail & Related papers  (2022-04-01T06:22:23Z)
• PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Driven Adaptive Prior [103.00403682863427]
  We propose PriorGrad to improve the efficiency of the conditional diffusion model. We show that PriorGrad achieves a faster convergence leading to data and parameter efficiency and improved quality.
  arXiv  Detail & Related papers  (2021-06-11T14:04:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.