Imagen de Portada

Loss Functions in Diffusion Models: A Comparative Study

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kumar, Dibyanshu, Vaeth, Philipp, Gregorová, Magda
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

Diffusion Classifier Guidance for Non-robust Classifiers
por: Vaeth, Philipp, et al.
Publicado: (2025)

Generative Example-Based Explanations: Bridging the Gap between Generative Modeling and Explainability
por: Vaeth, Philipp, et al.
Publicado: (2024)

GradCheck: Analyzing classifier guidance gradients for conditional diffusion sampling
por: Vaeth, Philipp, et al.
Publicado: (2024)

Sugar-Beet Stress Detection using Satellite Image Time Series
por: Sadbhave, Bhumika Laxman, et al.
Publicado: (2025)

Discrete Graph Auto-Encoder
por: Boget, Yoann, et al.
Publicado: (2023)

A Comparative Study of Invariance-Aware Loss Functions for Deep Learning-based Gridless Direction-of-Arrival Estimation
por: Chen, Kuan-Lin, et al.
Publicado: (2025)

Leveraging Pretrained Language Models as Energy Functions for Glauber Dynamics Text Diffusion
por: Kathuria, Tarun, et al.
Publicado: (2026)

Advancing Loss Functions in Recommender Systems: A Comparative Study with a Rényi Divergence-Based Solution
por: Zhang, Shengjia, et al.
Publicado: (2025)

A Diffusive Classification Loss for Learning Energy-based Generative Models
por: OuYang, RuiKang, et al.
Publicado: (2026)

AnyLoss: Transforming Classification Metrics into Loss Functions
por: Han, Doheon, et al.
Publicado: (2024)

Control Consistency Losses for Diffusion Bridges
por: Howard, Samuel, et al.
Publicado: (2025)

A Principled Loss Function for Direct Language Model Alignment
por: Tan, Yuandong
Publicado: (2025)

Imbalance-aware Presence-only Loss Function for Species Distribution Modeling
por: Zbinden, Robin, et al.
Publicado: (2024)

Improving GBDT Performance on Imbalanced Datasets: An Empirical Study of Class-Balanced Loss Functions
por: Luo, Jiaqi, et al.
Publicado: (2024)

Diffusion Model with Perceptual Loss
por: Lin, Shanchuan, et al.
Publicado: (2023)

A Multi-step Loss Function for Robust Learning of the Dynamics in Model-based Reinforcement Learning
por: Benechehab, Abdelhakim, et al.
Publicado: (2024)

Refining Diffusion Models for Motion Synthesis with an Acceleration Loss to Generate Realistic IMU Data
por: Häusler, Lars Ole, et al.
Publicado: (2025)

DLPO: Diffusion Model Loss-Guided Reinforcement Learning for Fine-Tuning Text-to-Speech Diffusion Models
por: Chen, Jingyi, et al.
Publicado: (2024)

Cut Your Losses in Large-Vocabulary Language Models
por: Wijmans, Erik, et al.
Publicado: (2024)

Temperature-Free Loss Function for Contrastive Learning
por: Kim, Bum Jun, et al.
Publicado: (2025)

Loss Functions and Operators Generated by f-Divergences
por: Roulet, Vincent, et al.
Publicado: (2025)

A Unifying Generator Loss Function for Generative Adversarial Networks
por: Veiner, Justin, et al.
Publicado: (2023)

On the Hyperparameter Loss Landscapes of Machine Learning Models: An Exploratory Study
por: Huang, Mingyu, et al.
Publicado: (2023)

Interval Regression: A Comparative Study with Proposed Models
por: Nguyen, Tung L, et al.
Publicado: (2025)

Ratio-based Loss Functions
por: Helgerth, Lena, et al.
Publicado: (2026)

Custom Loss Functions in Fuel Moisture Modeling
por: Hirschi, Jonathon
Publicado: (2025)

A Note on Loss Functions and Error Compounding in Model-based Reinforcement Learning
por: Jiang, Nan
Publicado: (2024)

A Fair Loss Function for Network Pruning
por: Meyer, Robbie, et al.
Publicado: (2022)

A Versatile Influence Function for Data Attribution with Non-Decomposable Loss
por: Deng, Junwei, et al.
Publicado: (2024)

MVG-CRPS: A Robust Loss Function for Multivariate Probabilistic Forecasting
por: Zheng, Vincent Zhihao, et al.
Publicado: (2024)

Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes
por: Kiselev, Nikita, et al.
Publicado: (2024)

Rethinking Losses for Diffusion Bridge Samplers
por: Sanokowski, Sebastian, et al.
Publicado: (2025)

Scaling Session-Based Transformer Recommendations using Optimized Negative Sampling and Loss Functions
por: Wilm, Timo, et al.
Publicado: (2023)

Dimension-Free Decision Calibration for Nonlinear Loss Functions
por: Tang, Jingwu, et al.
Publicado: (2025)

Improved Balanced Classification with Theoretically Grounded Loss Functions
por: Cortes, Corinna, et al.
Publicado: (2025)

Semantic Loss Functions for Neuro-Symbolic Structured Prediction
por: Ahmed, Kareem, et al.
Publicado: (2024)

A Comparative Study of Model Selection Criteria for Symbolic Regression
por: Soltani, Ali, et al.
Publicado: (2026)

Demystifying Diffusion Objectives: Reweighted Losses are Better Variational Bounds
por: Shi, Jiaxin, et al.
Publicado: (2025)

A Comparative Study of Model Adaptation Strategies for Multi-Treatment Uplift Modeling
por: Zhang, Ruyue, et al.
Publicado: (2025)

On Evaluating Loss Functions for Stock Ranking: An Empirical Analysis With Transformer Model
por: Kwiatkowski, Jan, et al.
Publicado: (2025)