Cover Image

Diffusion Models under Alternative Noise: Simplified Analysis and Sensitivity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Choi, Juhyeok, Fan, Chenglin
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Advancing atomic electron tomography with neural networks
by: Lee, Juhyeok, et al.
Published: (2025)

Alternators With Noise Models
by: Rezaei, Mohammad R., et al.
Published: (2025)

Noise is All You Need: Private Second-Order Convergence of Noisy SGD
by: Avdiukhin, Dmitrii, et al.
Published: (2024)

Sensitivity Analysis for Diffusion Models
by: Scarvelis, Christopher, et al.
Published: (2025)

Robust and Consistent Ski Rental with Distributional Advice
by: Kim, Jihwan, et al.
Published: (2026)

DP-Muon: Differentially Private Optimization via Matrix-Orthogonalized Momentum
by: Kim, Jihwan, et al.
Published: (2026)

Simplified and Generalized Masked Diffusion for Discrete Data
by: Shi, Jiaxin, et al.
Published: (2024)

Simplified Diffusion Schrödinger Bridge
by: Tang, Zhicong, et al.
Published: (2024)

Label-Noise Robust Diffusion Models
by: Na, Byeonghu, et al.
Published: (2024)

Learning Augmented Graph $k$-Clustering
by: Fan, Chenglin, et al.
Published: (2025)

DiSK: Differentially Private Optimizer with Simplified Kalman Filter for Noise Reduction
by: Zhang, Xinwei, et al.
Published: (2024)

Inference-Time Alignment of Diffusion Models with Direct Noise Optimization
by: Tang, Zhiwei, et al.
Published: (2024)

Diffusion Model with Representation Alignment for Protein Inverse Folding
by: Wang, Chenglin, et al.
Published: (2024)

Noise Matters: Diffusion Model-based Urban Mobility Generation with Collaborative Noise Priors
by: Zhang, Yuheng, et al.
Published: (2024)

Antithetic Noise in Diffusion Models
by: Jia, Jing, et al.
Published: (2025)

A Probabilistic Formulation of Offset Noise in Diffusion Models
by: Kutsuna, Takuro
Published: (2024)

Model Sparsity Can Simplify Machine Unlearning
by: Jia, Jinghan, et al.
Published: (2023)

Risk-Sensitive Diffusion: Robustly Optimizing Diffusion Models with Noisy Samples
by: Li, Yangming, et al.
Published: (2024)

Less Noise, Same Certificate: Retain Sensitivity for Unlearning
by: Heinzler, Carolin, et al.
Published: (2026)

NoiseAR: AutoRegressing Initial Noise Prior for Diffusion Models
by: Li, Zeming, et al.
Published: (2025)

Simplifying Transformer Blocks
by: He, Bobby, et al.
Published: (2023)

Simplified PCNet with Robustness
by: Li, Bingheng, et al.
Published: (2024)

Noise Schedule Design for Diffusion Models: An Optimal Control Perspective
by: Kong, Seo Taek, et al.
Published: (2026)

Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models
by: Lu, Cheng, et al.
Published: (2024)

Efficient Conformal Prediction for Regression Models under Label Noise
by: Cohen, Yahav, et al.
Published: (2025)

Interpretability Illusions in the Generalization of Simplified Models
by: Friedman, Dan, et al.
Published: (2023)

NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training
by: Wu, Fang, et al.
Published: (2026)

Learning-Augmented Ski Rental with Discrete Distributions: A Bayesian Approach
by: Kang, Bosun, et al.
Published: (2025)

Learning under Label Noise through Few-Shot Human-in-the-Loop Refinement
by: Saeed, Aaqib, et al.
Published: (2024)

Test-Time Scaling of Diffusion Models via Noise Trajectory Search
by: Ramesh, Vignav, et al.
Published: (2025)

Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models
by: Kahouli, Khaled, et al.
Published: (2025)

Simplifying Latent Dynamics with Softly State-Invariant World Models
by: Saanum, Tankred, et al.
Published: (2024)

Simplifying Graph Kernels for Efficient
by: Wang, Lin, et al.
Published: (2025)

Simplifying the Theory on Over-Smoothing
by: Roth, Andreas
Published: (2024)

Noise as a Probe: Membership Inference Attacks on Diffusion Models Leveraging Initial Noise
by: Lian, Puwei, et al.
Published: (2026)

Evaluating the Sensitivity of BiLSTM Forecasting Models to Sequence Length and Input Noise
by: Albelali, Salma, et al.
Published: (2025)

A Noise Sensitivity Exponent Controls Large Statistical-to-Computational Gaps in Single- and Multi-Index Models
by: Defilippis, Leonardo, et al.
Published: (2026)

Regretful Decisions under Label Noise
by: Nagaraj, Sujay, et al.
Published: (2025)

Manifold Fitting under Unbounded Noise
by: Yao, Zhigang, et al.
Published: (2019)

Robust Learning under Hybrid Noise
by: Wei, Yang, et al.
Published: (2024)