Imagen de Portada

SFBD Flow: A Continuous-Optimization Framework for Training Diffusion Models with Noisy Samples

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lu, Haoye, Lo, Darren, Yu, Yaoliang
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SFBD-OMNI: Bridge models for lossy measurement restoration with limited clean samples
por: Lu, Haoye, et al.
Publicado: (2025)

Stochastic Forward-Backward Deconvolution: Training Diffusion Models with Finite Noisy Datasets
por: Lu, Haoye, et al.
Publicado: (2025)

Structure Preserving Diffusion Models
por: Lu, Haoye, et al.
Publicado: (2024)

One Sample Fits All: Approximating All Probabilistic Values Simultaneously and Efficiently
por: Li, Weida, et al.
Publicado: (2024)

A Unified Framework for Gradient Aggregation in Multi-Objective Optimization
por: Hu, Zeou, et al.
Publicado: (2026)

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

Efficient Bilevel Optimization with KFAC-Based Hypergradients
por: Liao, Disen, et al.
Publicado: (2026)

Disguised Copyright Infringement of Latent Diffusion Models
por: Lu, Yiwei, et al.
Publicado: (2024)

Indiscriminate Data Poisoning Attacks on Neural Networks
por: Lu, Yiwei, et al.
Publicado: (2022)

Semi-Variance Reduction for Fair Federated Learning
por: Malekmohammadi, Saber, et al.
Publicado: (2024)

DiffBreak: Is Diffusion-Based Purification Robust?
por: Kassis, Andre, et al.
Publicado: (2024)

A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD
por: Jin, Ruinan, et al.
Publicado: (2024)

Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning
por: Duan, Wenchang, et al.
Publicado: (2025)

Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers
por: Lu, Yiwei, et al.
Publicado: (2024)

Temporal Score Rescaling for Temperature Sampling in Diffusion and Flow Models
por: Xu, Yanbo, et al.
Publicado: (2025)

$f$-MICL: Understanding and Generalizing InfoNCE-based Contrastive Learning
por: Lu, Yiwei, et al.
Publicado: (2024)

MobiGPT: A Foundation Model for Mobile Wireless Networks
por: Qi, Xiaoqian, et al.
Publicado: (2025)

BridgePure: Limited Protection Leakage Can Break Black-Box Data Protection
por: Wang, Yihan, et al.
Publicado: (2024)

TreeGrad-Ranker: Feature Ranking via $O(L)$-Time Gradients for Decision Trees
por: Li, Weida, et al.
Publicado: (2026)

Provably Adaptive Linear Approximation for the Shapley Value and Beyond
por: Li, Weida, et al.
Publicado: (2026)

An Operator Splitting View of Federated Learning
por: Malekmohammadi, Saber, et al.
Publicado: (2021)

Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching
por: Gaur, Mudit, et al.
Publicado: (2025)

Balanced Training of Energy-Based Models with Adaptive Flow Sampling
por: Grenioux, Louis, et al.
Publicado: (2023)

GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models
por: Holderrieth, Peter, et al.
Publicado: (2025)

Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control
por: Rahn, Nate, et al.
Publicado: (2023)

Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors
por: Lu, Yiwei, et al.
Publicado: (2024)

Hard Negative Sample-Augmented DPO Post-Training for Small Language Models
por: Lu, Haocheng, et al.
Publicado: (2025)

NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization
por: Liu, Enshu, et al.
Publicado: (2026)

Convergence to Nash Equilibrium and No-regret Guarantee in (Markov) Potential Games
por: Dong, Jing, et al.
Publicado: (2024)

The Representation-Rationalizability Tradeoff in Reward Learning
por: Dong, Jing, et al.
Publicado: (2026)

Diffusion Models with Heavy-Tailed Targets: Score Estimation and Sampling Guarantees
por: Yu, Yifeng, et al.
Publicado: (2026)

UoMo: A Universal Model of Mobile Traffic Forecasting for Wireless Network Optimization
por: Chai, Haoye, et al.
Publicado: (2024)

$α$-Flow: A Unified Framework for Continuous-State Discrete Flow Matching Models
por: Cheng, Chaoran, et al.
Publicado: (2025)

LiLAW: Lightweight Learnable Adaptive Weighting to Learn Sample Difficulty & Improve Noisy Training
por: Moturu, Abhishek, et al.
Publicado: (2025)

Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problems
por: Meng, Xiangming, et al.
Publicado: (2022)

Robust Learning of Diffusion Models with Extremely Noisy Conditions
por: Chen, Xin, et al.
Publicado: (2025)

Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training
por: Greenewald, Kristjan, et al.
Publicado: (2024)

Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data
por: Daras, Giannis, et al.
Publicado: (2024)

Neural Global Optimization via Iterative Refinement from Noisy Samples
por: Muzaffar, Qusay, et al.
Publicado: (2026)

Diffusion Posterior Sampling for General Noisy Inverse Problems
por: Chung, Hyungjin, et al.
Publicado: (2022)