Technology Category
Computer Vision: Diffusion Models for VisionSearch and Optimization: Learning to SearchMachine Learning: Optimization
Optimizing Input of Denoising Score Matching is Biased Towards Higher Score Norm
🤖 AI Summary
This work identifies an inherent bias in diffusion models when optimizing conditional inputs via denoising score matching: the optimization breaks theoretical equivalence with exact score matching and systematically inflates the norm of the score function. Method: Leveraging score matching theory and the diffusion framework, the authors derive a rigorous mathematical characterization and quantitative model of this bias, proving it arises from perturbations to score estimation induced by input optimization—and showing that analogous bias occurs even under pre-trained model-based data distribution optimization. Contribution/Results: The analysis establishes the bias’s cross-method universality, confirming its presence in prominent approaches including MAR, PerCo, and DreamFusion. Beyond delivering a critical theoretical warning for existing methods, the work provides foundational insights for designing optimization strategies that mitigate score-norm inflation—advancing both the theoretical understanding and practical design of conditional diffusion modeling.
Technology Category
Application Category
📝 Abstract
Many recent works utilize denoising score matching to optimize the conditional input of diffusion models. In this workshop paper, we demonstrate that such optimization breaks the equivalence between denoising score matching and exact score matching. Furthermore, we show that this bias leads to higher score norm. Additionally, we observe a similar bias when optimizing the data distribution using a pre-trained diffusion model. Finally, we discuss the wide range of works across different domains that are affected by this bias, including MAR for auto-regressive generation, PerCo for image compression, and DreamFusion for text to 3D generation.
Problem
Research questions and friction points this paper is trying to address.
Optimizing denoising score matching input introduces bias in diffusion models
This bias breaks equivalence between denoising and exact score matching
The bias affects various applications like image compression and 3D generation
Innovation
Methods, ideas, or system contributions that make the work stand out.
Optimizing denoising score matching introduces bias
Bias increases score norm in diffusion models
Affects auto-regressive generation and text-to-3D systems
🔎 Similar Papers
No similar papers found.
