Imagen de Portada

From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster training

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Berner, Julius, Richter, Lorenz, Sendera, Marcin, Rector-Brooks, Jarrid, Malkin, Nikolay
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

Improved off-policy training of diffusion samplers
por: Sendera, Marcin, et al.
Publicado: (2024)

Adaptive teachers for amortized samplers
por: Kim, Minsu, et al.
Publicado: (2024)

Improved sampling via learned diffusions
por: Richter, Lorenz, et al.
Publicado: (2023)

Solving Bayesian inverse problems with diffusion priors and off-policy RL
por: Scimeca, Luca, et al.
Publicado: (2025)

An optimal control perspective on diffusion-based generative modeling
por: Berner, Julius, et al.
Publicado: (2022)

Amortizing intractable inference in diffusion models for vision, language, and control
por: Venkatraman, Siddarth, et al.
Publicado: (2024)

Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
por: Akhound-Sadegh, Tara, et al.
Publicado: (2024)

Improving and generalizing flow-based generative models with minibatch optimal transport
por: Tong, Alexander, et al.
Publicado: (2023)

Bridging discrete and continuous state spaces: Exploring the Ehrenfest process in time-continuous diffusion models
por: Winkler, Ludwig, et al.
Publicado: (2024)

Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models
por: Venkatraman, Siddarth, et al.
Publicado: (2025)

Underdamped Diffusion Bridges with Applications to Sampling
por: Blessing, Denis, et al.
Publicado: (2025)

On scalable and efficient training of diffusion samplers
por: Kim, Minkyu, et al.
Publicado: (2025)

Bridge Matching Sampler: Scalable Sampling via Generalized Fixed-Point Diffusion Matching
por: Blessing, Denis, et al.
Publicado: (2026)

Hi-fi functional priors by learning activations
por: Sendera, Marcin, et al.
Publicado: (2025)

Revisiting the Equivalence of Bayesian Neural Networks and Gaussian Processes: On the Importance of Learning Activations
por: Sendera, Marcin, et al.
Publicado: (2024)

Cometh: A continuous-time discrete-state graph diffusion model
por: Siraudin, Antoine, et al.
Publicado: (2024)

Data-to-Energy Stochastic Dynamics
por: Tamogashev, Kirill, et al.
Publicado: (2025)

Sequential Controlled Langevin Diffusions
por: Chen, Junhua, et al.
Publicado: (2024)

Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference
por: Blessing, Denis, et al.
Publicado: (2025)

Planner Aware Path Learning in Diffusion Language Models Training
por: Peng, Fred Zhangzhi, et al.
Publicado: (2025)

On Bellman equations for continuous-time policy evaluation I: discretization and approximation
por: Mou, Wenlong, et al.
Publicado: (2024)

Path Planning for Masked Diffusion Model Sampling
por: Peng, Fred Zhangzhi, et al.
Publicado: (2025)

On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning
por: Proszewska, Magdalena, et al.
Publicado: (2025)

Dynamical Measure Transport and Neural PDE Solvers for Sampling
por: Sun, Jingtong, et al.
Publicado: (2024)

Towards accurate extreme event likelihoods from diffusion model climate emulators
por: Manshausen, Peter, et al.
Publicado: (2026)

SEMU: Singular Value Decomposition for Efficient Machine Unlearning
por: Sendera, Marcin, et al.
Publicado: (2025)

On Generalization for Generative Flow Networks
por: Krichel, Anas, et al.
Publicado: (2024)

Accelerating trajectory optimization with Sobolev-trained diffusion policies
por: Hellard, Théotime Le, et al.
Publicado: (2026)

One step further with Monte-Carlo sampler to guide diffusion better
por: Ren, Minsi, et al.
Publicado: (2026)

LEAPS: A discrete neural sampler via locally equivariant networks
por: Holderrieth, Peter, et al.
Publicado: (2025)

SE(3)-Stochastic Flow Matching for Protein Backbone Generation
por: Bose, Avishek Joey, et al.
Publicado: (2023)

Solving Poisson Equations using Neural Walk-on-Spheres
por: Nam, Hong Chul, et al.
Publicado: (2024)

RNE: plug-and-play diffusion inference-time control and energy-based training
por: He, Jiajun, et al.
Publicado: (2025)

In-Context Parametric Inference: Point or Distribution Estimators?
por: Mittal, Sarthak, et al.
Publicado: (2025)

Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction
por: Rector-Brooks, Jarrid, et al.
Publicado: (2024)

Synthesis of discrete-continuous quantum circuits with multimodal diffusion models
por: Fürrutter, Florian, et al.
Publicado: (2025)

Discrete Probabilistic Inference as Control in Multi-path Environments
por: Deleu, Tristan, et al.
Publicado: (2024)

A Gibbs posterior sampler for inverse problem based on prior diffusion model
por: Giovannelli, Jean-François
Publicado: (2026)

Mixing times of data-augmentation Gibbs samplers for high-dimensional probit regression
por: Ascolani, Filippo, et al.
Publicado: (2025)

Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation
por: Huguet, Guillaume, et al.
Publicado: (2024)