Variance-Aware Adaptive Weighting for Diffusion Model Training
Diffusion models have recently achieved remarkable success in generative modeling, yet their training dynamics across different noise levels remain highly imbalanced, which can lead to inefficient optimization and unstable learning behavior. In this work, we investigate this imbalance from the perspective of loss variance across log-SNR levels and propose a variance-aware adaptive weighting strategy to address it. The proposed approach dynamically adjusts training weights based on the observed variance distribution, encouraging a more balanced optimization process across noise levels. Extensive experiments on CIFAR-10 and CIFAR-100 demonstrate that the proposed method consistently improves generative performance over standard training schemes, achieving lower Fréchet Inception Distance (FID) while also reducing performance variance across random seeds. Additional analysis, including loss-log-SNR visualization, variance heatmaps, and ablation studies, further reveal that the adaptive weighting effectively stabilizes training dynamics. These results highlight the potential of variance-aware training strategies for improving diffusion model optimization.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Variance-Aware Loss Scheduling for Multimodal Alignment in Low-Data Settings
Training vision-language models for image-text alignment typically requires large datasets to achieve robust performance. In low-data scenarios, standard contrastive learning can struggle to align modalities effectively …
Contrastive LearningImage-text RetrievalSchedulingText RetrievalUnsupervised Denoising of Diffusion-Weighted Images with Bias and Variance Corrected Noise Modeling
Diffusion magnetic resonance imaging (dMRI) plays a vital role in both clinical diagnostics and neuroscience research. However, its inherently low signal-to-noise ratio (SNR), especially under high diffusion weighting, s…
MAPLE: Modality-Aware Post-training and Learning Ecosystem
Multimodal language models now integrate text, audio, and video for unified reasoning. Yet existing RL post-training pipelines treat all input signals as equally relevant, ignoring which modalities each task actually req…
Adaptive Non-Uniform Timestep Sampling for Diffusion Model Training
As a highly expressive generative model, diffusion models have demonstrated exceptional success across various domains, including image generation, natural language processing, and combinatorial optimization. However, as…
Image GenerationSchedulingAdaptive Non-Uniform Timestep Sampling for Accelerating Diffusion Model Training
As a highly expressive generative model, diffusion models have demonstrated exceptional success across various domains, including image generation, natural language processing, and combinatorial optimization. However…
Combinatorial OptimizationImage GenerationScheduling