Image de couverture de livre

Energy-Based Modelling for Discrete and Mixed Data via Heat Equations on Structured Spaces

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Schröder, Tobias, Ou, Zijing, Li, Yingzhen, Duncan, Andrew B.
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Inference-Time Scaling of Discrete Diffusion Models via Importance Weighting and Optimal Proposal Design
par: Ou, Zijing, et autres
Publié: (2025)

Discrete Neural Flow Samplers with Locally Equivariant Transformer
par: Ou, Zijing, et autres
Publié: (2025)

Neural Flow Samplers with Shortcut Models
par: Chen, Wuhao, et autres
Publié: (2025)

TabRep: Training Tabular Diffusion Models with a Simple and Effective Continuous Representation
par: Si, Jacob, et autres
Publié: (2025)

Mutual Information Multinomial Estimation
par: Chen, Yanzhi, et autres
Publié: (2024)

Improving Probabilistic Diffusion Models With Optimal Diagonal Covariance Matching
par: Ou, Zijing, et autres
Publié: (2024)

Memory-Driven Self-Improvement for Decision Making with Large Language Models
par: Yan, Xue, et autres
Publié: (2025)

Missing Data Imputation Based on Dynamically Adaptable Structural Equation Modeling with Self-Attention
par: Deng, Ou, et autres
Publié: (2023)

Free energy Estimation on Any State Space
par: He, Jiajun, et autres
Publié: (2026)

Diffusion Alignment Beyond KL: Variance Minimisation as Effective Policy Optimiser
par: Ou, Zijing, et autres
Publié: (2026)

Calibrating Transformers via Sparse Gaussian Processes
par: Chen, Wenlong, et autres
Publié: (2023)

Deep Optimal Sensor Placement for Black Box Stochastic Simulations
par: Cordero-Encinar, Paula, et autres
Publié: (2024)

Sharp Generalization for Nonparametric Regression in Interpolation Space by Over-Parameterized Neural Networks Trained with Preconditioned Gradient Descent and Early Stopping
par: Yang, Yingzhen, et autres
Publié: (2024)

HiBBO: HiPPO-based Space Consistency for High-dimensional Bayesian Optimisation
par: Xuan, Junyu, et autres
Publié: (2025)

Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion
par: Zhang, Ruixiang, et autres
Publié: (2025)

Structured Coupling for Flow Matching
par: Sumba, Xavier, et autres
Publié: (2026)

Diffusion on Graph: Augmentation of Graph Structure for Node Classification
par: Wang, Yancheng, et autres
Publié: (2025)

Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions
par: Kiyohara, Naoki, et autres
Publié: (2025)

Identifying Nonstationary Causal Structures with High-Order Markov Switching Models
par: Balsells-Rodas, Carles, et autres
Publié: (2024)

VarDiU: A Variational Diffusive Upper Bound for One-Step Diffusion Distillation
par: Wang, Leyang, et autres
Publié: (2025)

Dimension-Free Convergence of Discrete Diffusion Models: Adjoint Equations Induce the Right Space
par: Kan, Kelvin, et autres
Publié: (2026)

Efficient Antibody Structure Refinement Using Energy-Guided SE(3) Flow Matching
par: Zhang, Jiying, et autres
Publié: (2024)

Shallow Neural Networks Learn Low-Degree Spherical Polynomials with Feature Learning by Learnable Channel Attention
par: Yang, Yingzhen
Publié: (2025)

Structure-Preserving Gaussian Processes Via Discrete Euler-Lagrange Equations
par: Ewering, Jan-Hendrik, et autres
Publié: (2026)

Permutation-Based Rank Test in the Presence of Discretization and Application in Causal Discovery with Mixed Data
par: Dong, Xinshuai, et autres
Publié: (2025)

From Static Structures to Ensembles: Studying and Harnessing Protein Structure Tokenization
par: Liu, Zijing, et autres
Publié: (2025)

Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
par: Ou, Jingyang, et autres
Publié: (2024)

Improved Generalization Bounds for Transductive Learning by Transductive Local Complexity and Its Applications
par: Yang, Yingzhen
Publié: (2023)

Gradient Descent Finds Over-Parameterized Neural Networks with Sharp Generalization for Nonparametric Regression
par: Yang, Yingzhen, et autres
Publié: (2024)

Gradient Descent with Projection Finds Over-Parameterized Neural Networks for Learning Low-Degree Polynomials with Nearly Minimax Optimal Rate
par: Yang, Yingzhen, et autres
Publié: (2026)

Projective Proximal Gradient Descent for A Class of Nonconvex Nonsmooth Optimization Problems: Fast Convergence Without Kurdyka-Lojasiewicz (KL) Property
par: Yang, Yingzhen, et autres
Publié: (2023)

Neural Mutual Information Estimation with Vector Copulas
par: Chen, Yanzhi, et autres
Publié: (2025)

Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients
par: Alvo, Matias, et autres
Publié: (2026)

Energy-Based Models with Applications to Speech and Language Processing
par: Ou, Zhijian
Publié: (2024)

Extraction and Recovery of Spatio-Temporal Structure in Latent Dynamics Alignment with Diffusion Models
par: Wang, Yule, et autres
Publié: (2023)

Statistical-Neural Interaction Networks for Interpretable Mixed-Type Data Imputation
par: Deng, Ou, et autres
Publié: (2026)

WildCat: Near-Linear Attention in Theory and Practice
par: Schröder, Tobias, et autres
Publié: (2026)

MixMax: Distributional Robustness in Function Space via Optimal Data Mixtures
par: Thudi, Anvith, et autres
Publié: (2024)

Improving Discrete Diffusion Models via Structured Preferential Generation
par: Rissanen, Severi, et autres
Publié: (2024)

DICE: Discrete inverse continuity equation for learning population dynamics
par: Blickhan, Tobias, et autres
Publié: (2025)