Optimizing Input of Denoising Score Matching is Biased Towards Higher Score Norm

Tongda Xu
11/13/2025
cs.LGcs.CV

No confident code implementation found for this paper. 1 possible match can be shown below.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Why Heuristic Weighting Works: A Theoretical Analysis of Denoising Score Matching

87% match2025

Rectified Diffusion Guidance for Conditional Generation

86% match1 repo62026

Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generation

86% match2025

Denoising Score Matching with Random Features: Insights on Diffusion Models from Precise Learning Curves

86% match2025

Training-free Diffusion Model Alignment with Sampling Demons

86% match3 repos252026

FIND: Fine-tuning Initial Noise Distribution with Policy Optimization for Diffusion Models

86% match2 repos152024

Cite this paper

@article{xu2025optimizing,
  title  = {Optimizing Input of Denoising Score Matching is Biased Towards Higher Score Norm},
  author = {Tongda Xu},
  year   = {2025},
  eprint = {2511.11727},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2511.11727v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2511.11727.svg)](https://codeofpaper.com/paper/2511.11727)

Discussion