Imagen de Portada

Do Heavy Tails Help Diffusion? On the Subtle Trade-off Between Initialization and Training

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cherkaoui, Hamza, Halconruy, Hélène, Ocello, Antonio
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

When to Transfer: Adaptive Source Selection for Positive Transfer in Linear Models
por: Cherkaoui, Hamza, et al.
Publicado: (2025)

Learning Upper Lower Value Envelopes to Shape Online RL: A Principled Approach
por: Reboul, Sebastian, et al.
Publicado: (2025)

Tessellation Localized Transfer learning for nonparametric regression
por: Halconruy, Hélène, et al.
Publicado: (2026)

Heavy-Tailed Diffusion Models
por: Pandey, Kushagra, et al.
Publicado: (2024)

Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distance
por: Gentiloni-Silveri, Marta, et al.
Publicado: (2025)

Learning the Infinitesimal Generator of Stochastic Diffusion Processes
por: Kostic, Vladimir R., et al.
Publicado: (2024)

Adaptive Sample Sharing for Multi Agent Linear Bandits
por: Cherkaoui, Hamza, et al.
Publicado: (2023)

Self-Regulating Annealing in Heavy-Tailed Diffusion Models
por: Wakatsuki, Keito, et al.
Publicado: (2026)

Heavy-Tailed Diffusion with Denoising Lévy Probabilistic Models
por: Shariatian, Dario, et al.
Publicado: (2024)

Tail Annealing for Heavy-Tailed Flow Matching
por: Pachebat, Jean
Publicado: (2026)

Bit-Level Discrete Diffusion with Markov Probabilistic Models: An Improved Framework with Sharp Convergence Bounds under Minimal Assumptions
por: Pham, Le-Tuyet-Nhi, et al.
Publicado: (2025)

Asynchronous Heavy-Tailed Optimization
por: Sun, Junfei, et al.
Publicado: (2026)

Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD
por: Wan, Yijun, et al.
Publicado: (2023)

Wasserstein Convergence of Critically Damped Langevin Diffusions
por: Strasman, Stanislas, et al.
Publicado: (2025)

Bilateral Trade Under Heavy-Tailed Valuations: Minimax Regret with Infinite Variance
por: Zhao, Hangyi
Publicado: (2026)

Heavy-Tailed Principal Component Analysis
por: Sayde, Mario, et al.
Publicado: (2026)

Models of Heavy-Tailed Mechanistic Universality
por: Hodgkinson, Liam, et al.
Publicado: (2025)

Architecture Selection via the Trade-off Between Accuracy and Robustness
por: Deng, Zhun, et al.
Publicado: (2019)

Laplace Transform Based Low-Complexity Learning of Continuous Markov Semigroups
por: Kostic, Vladimir R., et al.
Publicado: (2024)

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

Muon: Training and Trade-offs with Latent Attention and MoE
por: Mehta, Sushant, et al.
Publicado: (2025)

Stochastic Bilevel Optimization with Heavy-Tailed Noise
por: Liu, Zhuanghua, et al.
Publicado: (2025)

Regret Distribution in Stochastic Bandits: Optimal Trade-off between Expectation and Tail Risk
por: Simchi-Levi, David, et al.
Publicado: (2023)

AgriPath: A Systematic Exploration of Architectural Trade-offs for Crop Disease Classification
por: Mooraj, Hamza, et al.
Publicado: (2026)

The insider problem in the trinomial model: a discrete-time jump process approach
por: Halconruy, Hélène
Publicado: (2021)

Malliavin calculus for marked binomial processes: portfolio optimisation in the trinomial model and compound Poisson approximation
por: Halconruy, Hélène
Publicado: (2021)

Heavy-Tail Phenomenon in Decentralized SGD
por: Gurbuzbalaban, Mert, et al.
Publicado: (2022)

Balancing the Budget: Understanding Trade-offs Between Supervised and Preference-Based Finetuning
por: Raghavendra, Mohit, et al.
Publicado: (2025)

Stability and Generalization of Nonconvex Optimization with Heavy-Tailed Noise
por: Chen, Hongxu, et al.
Publicado: (2026)

On Forgetting and Stability of Score-based Generative models
por: Strasman, Stanislas, et al.
Publicado: (2026)

Efficient Distributed Optimization under Heavy-Tailed Noise
por: Lee, Su Hyeong, et al.
Publicado: (2025)

ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs
por: Kang, Wonjun, et al.
Publicado: (2025)

On a Projection Least Squares Estimator for Jump Diffusion Processes
por: Halconruy, Hélène, et al.
Publicado: (2022)

Clip Body and Tail Separately: High Probability Guarantees for DPSGD with Heavy Tails
por: Sha, Haichao, et al.
Publicado: (2024)

Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean-Field Games
por: Ocello, Antonio, et al.
Publicado: (2025)

Can SGD Handle Heavy-Tailed Noise?
por: Fatkhullin, Ilyas, et al.
Publicado: (2025)

Adaptive Heavy-Tailed Stochastic Gradient Descent
por: Gong, Bodu, et al.
Publicado: (2025)

Best-of-Both-Worlds for Heavy-Tailed Markov Decision Processes
por: Chen, Yu, et al.
Publicado: (2026)

On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance
por: Tang, Qiaoyue, et al.
Publicado: (2025)

Time-Varying Graph Learning for Data with Heavy-Tailed Distribution
por: Javaheri, Amirhossein, et al.
Publicado: (2024)