Cover Image

Breaking AR's Sampling Bottleneck: Provable Acceleration via Diffusion Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Gen, Cai, Changxiao
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Information Theory Statistics Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Minimax Optimality of the Probability Flow ODE for Diffusion Models
by: Cai, Changxiao, et al.
Published: (2025)

Confidence-Based Decoding is Provably Efficient for Diffusion Language Models
by: Cai, Changxiao, et al.
Published: (2026)

Adaptation to Intrinsic Dependence in Diffusion Language Models
by: Zhao, Yunxiao, et al.
Published: (2026)

Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions
by: Wu, Jingda, et al.
Published: (2026)

Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis
by: Li, Gen, et al.
Published: (2021)

Dimension-Free Convergence of Diffusion Models for Approximate Gaussian Mixtures
by: Li, Gen, et al.
Published: (2025)

Are First-Order Diffusion Samplers Really Slower? A Fast Forward-Value Approach
by: Jiao, Yuchen, et al.
Published: (2025)

Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model
by: Li, Gen, et al.
Published: (2020)

Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models
by: Li, Gen, et al.
Published: (2023)

Provable Efficiency of Guidance in Diffusion Models for General Data Distribution
by: Li, Gen, et al.
Published: (2025)

Breaking the Finite-Sample Barrier in Entropy Coupling
by: Asoodeh, Shahab, et al.
Published: (2026)

Settling the Sample Complexity of Model-Based Offline Reinforcement Learning
by: Li, Gen, et al.
Published: (2022)

Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees
by: Dmitriev, Daniil, et al.
Published: (2026)

Transfer Learning for Contextual Multi-armed Bandits
by: Cai, Changxiao, et al.
Published: (2022)

Towards a mathematical theory for consistency training in diffusion models
by: Li, Gen, et al.
Published: (2024)

The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model
by: Shi, Laixi, et al.
Published: (2023)

Minimax-optimal trust-aware multi-armed bandits
by: Cai, Changxiao, et al.
Published: (2024)

Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning
by: Cheng, Ziheng, et al.
Published: (2025)

A non-asymptotic distributional theory of approximate message passing for sparse and robust regression
by: Li, Gen, et al.
Published: (2024)

Accelerating Convergence of Score-Based Diffusion Models, Provably
by: Li, Gen, et al.
Published: (2024)

Model-Based Reinforcement Learning for Offline Zero-Sum Markov Games
by: Yan, Yuling, et al.
Published: (2022)

Characterizing Dependence of Samples along the Langevin Dynamics and Algorithms via Contraction of $Φ$-Mutual Information
by: Liang, Jiaming, et al.
Published: (2024)

Provable Acceleration for Diffusion Models under Minimal Assumptions
by: Li, Gen, et al.
Published: (2024)

Agnostic Sample Compression Schemes for Regression
by: Attias, Idan, et al.
Published: (2018)

Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound Assumptions
by: Zhang, Kaihong, et al.
Published: (2024)

Minimax-Optimal Reward-Agnostic Exploration in Reinforcement Learning
by: Li, Gen, et al.
Published: (2023)

The Sample Complexity of Simple Binary Hypothesis Testing
by: Pensia, Ankit, et al.
Published: (2024)

On the Sample Complexity of Robust Binary Hypothesis Testing
by: Vallinayagam, Shankar, et al.
Published: (2026)

Federated PCA and Estimation for Spiked Covariance Matrices: Optimal Rates and Efficient Algorithm
by: Li, Jingyang, et al.
Published: (2024)

Sequential 1-bit Mean Estimation with Near-Optimal Sample Complexity
by: Lau, Ivan, et al.
Published: (2025)

Distributed Nonparametric Estimation: from Sparse to Dense Samples per Terminal
by: Yuan, Deheng, et al.
Published: (2025)

Sample efficient inductive matrix completion with noise and inexact side information
by: Yang, Yuepeng, et al.
Published: (2026)

Improved Sample Complexity Bounds for Diffusion Model Training
by: Gupta, Shivam, et al.
Published: (2023)

The Sample Complexity of Distributed Simple Binary Hypothesis Testing under Information Constraints
by: Kazemi, Hadi, et al.
Published: (2025)

High-probability sample complexities for policy evaluation with linear function approximation
by: Li, Gen, et al.
Published: (2023)

Provable Diffusion Posterior Sampling for Bayesian Inversion
by: Chang, Jinyuan, et al.
Published: (2025)

Fine-Grained Uncertainty Quantification via Collisions
by: Friedbaum, Jesse, et al.
Published: (2024)

Mixed Regression via Approximate Message Passing
by: Tan, Nelvin, et al.
Published: (2023)

Variational Optimality of Föllmer Processes in Generative Diffusions
by: Chen, Yifan, et al.
Published: (2026)

Avoiding the Price of Adaptivity: Inference in Linear Contextual Bandits via Stability
by: Praharaj, Samya, et al.
Published: (2025)