Copertina

Diffusion-based Annealed Boltzmann Generators : benefits, pitfalls and hopes

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Grenioux, Louis, Noble, Maxence
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Improving the evaluation of samplers on multi-modal targets
di: Grenioux, Louis, et al.
Pubblicazione: (2025)

Learned Reference-based Diffusion Sampling for multi-modal distributions
di: Noble, Maxence, et al.
Pubblicazione: (2024)

Stochastic Localization via Iterative Posterior Sampling
di: Grenioux, Louis, et al.
Pubblicazione: (2024)

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

Temperature-Annealed Boltzmann Generators
di: Schopmans, Henrik, et al.
Pubblicazione: (2025)

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

On Sampling with Approximate Transport Maps
di: Grenioux, Louis, et al.
Pubblicazione: (2023)

Sampling from multi-modal distributions on Riemannian manifolds with training-free stochastic interpolants
di: Durmus, Alain, et al.
Pubblicazione: (2026)

Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities
di: Akhound-Sadegh, Tara, et al.
Pubblicazione: (2025)

Multi-Mode Quantum Annealing for Generative Representation Learning with Boltzmann Priors
di: Kim, Gilhan, et al.
Pubblicazione: (2026)

Riemannian Stochastic Interpolants for Amorphous Particle Systems
di: Grenioux, Louis, et al.
Pubblicazione: (2025)

Fast, faithful and photorealistic diffusion-based image super-resolution with enhanced Flow Map models
di: Noble, Maxence, et al.
Pubblicazione: (2026)

Quantum Boltzmann Machines using Parallel Annealing for Medical Image Classification
di: Schuman, Daniëlle, et al.
Pubblicazione: (2025)

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

Gradient-Guided Annealing for Domain Generalization
di: Ballas, Aristotelis, et al.
Pubblicazione: (2025)

Non-asymptotic Analysis of Diffusion Annealed Langevin Monte Carlo for Generative Modelling
di: Cordero-Encinar, Paula, et al.
Pubblicazione: (2025)

Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts
di: Skreta, Marta, et al.
Pubblicazione: (2025)

Towards Transfer Learning for Large-Scale Image Classification Using Annealing-based Quantum Boltzmann Machines
di: Schuman, Daniëlle, et al.
Pubblicazione: (2023)

Learning long range dependencies through time reversal symmetry breaking
di: Pourcel, Guillaume, et al.
Pubblicazione: (2025)

Towards training digitally-tied analog blocks via hybrid gradient computation
di: Nest, Timothy, et al.
Pubblicazione: (2024)

The pitfalls of next-token prediction
di: Bachmann, Gregor, et al.
Pubblicazione: (2024)

Transition Path Sampling with Boltzmann Generator-based MCMC Moves
di: Plainer, Michael, et al.
Pubblicazione: (2023)

On a few pitfalls in KL divergence gradient estimation for RL
di: Tang, Yunhao, et al.
Pubblicazione: (2025)

Lagrangian-based Equilibrium Propagation: generalisation to arbitrary boundary conditions & equivalence with Hamiltonian Echo Learning
di: Pourcel, Guillaume, et al.
Pubblicazione: (2025)

How to avoid machine learning pitfalls: a guide for academic researchers
di: Lones, Michael A.
Pubblicazione: (2021)

Transferable Boltzmann Generators
di: Klein, Leon, et al.
Pubblicazione: (2024)

SWAG: Long-term Surgical Workflow Prediction with Generative-based Anticipation
di: Boels, Maxence, et al.
Pubblicazione: (2024)

CBM-Dual: A 65-nm Fully Connected Chaotic Boltzmann Machine Processor for Dual Function Simulated Annealing and Reservoir Computing
di: Yoshioka, Kanta, et al.
Pubblicazione: (2026)

Learning Boltzmann Generators via Constrained Mass Transport
di: von Klitzing, Christopher, et al.
Pubblicazione: (2025)

GNN-MultiFix: Addressing the pitfalls for GNNs for multi-label node classification
di: Zhao, Tianqi, et al.
Pubblicazione: (2024)

CAX: Cellular Automata Accelerated in JAX
di: Faldor, Maxence, et al.
Pubblicazione: (2024)

Benchmarking Diffusion Annealing-Based Bayesian Inverse Problem Solvers
di: Crafts, Evan Scope, et al.
Pubblicazione: (2025)

Comparison of D-Wave Quantum Annealing and Markov Chain Monte Carlo for Sampling from a Probability Distribution of a Restricted Boltzmann Machine
di: Yazizi, Abdelmoula El, et al.
Pubblicazione: (2025)

Efficient and Unbiased Sampling from Boltzmann Distributions via Variance-Tuned Diffusion Models
di: Zhang, Fengzhe, et al.
Pubblicazione: (2025)

Non-asymptotic convergence bounds for Sinkhorn iterates and their gradients: a coupling approach
di: Greco, Giacomo, et al.
Pubblicazione: (2023)

Coarse-Grained Boltzmann Generators
di: Chen, Weilong, et al.
Pubblicazione: (2026)

Scalable Normalizing Flows Enable Boltzmann Generators for Macromolecules
di: Kim, Joseph C., et al.
Pubblicazione: (2024)

Scalable Equilibrium Sampling with Sequential Boltzmann Generators
di: Tan, Charlie B., et al.
Pubblicazione: (2025)

Beyond algorithm hyperparameters: on preprocessing hyperparameters and associated pitfalls in machine learning applications
di: Sauer, Christina, et al.
Pubblicazione: (2024)

Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation
di: Nitanda, Atsushi, et al.
Pubblicazione: (2026)