17 citations · 39 across the 17 of their papers we have counts for
21 papers
Transformer-Based Masked Diffusion Models Provably Learn Distributions with Latent Structure
Jingda Wu, Changxiao Cai
Masked diffusion models (MDMs) generate discrete data by iteratively unmasking multiple tokens in parallel using a learned mask predictor. Their output carries two errors: parallel…
Training Parallel Speculative Draft Models by Directly Minimizing Expected Decoding Rounds
Yunxiao Zhao, Changxiao Cai
Speculative decoding accelerates large language model inference by using a low-cost draft model to propose tokens that the full-size target model verifies in parallel. Parallel and…
ConvergeFlow: Language Flow with Provable Convergence to Token Embeddings
Na Li, Yuchen Jiao, Changxiao Cai +1
Recent advances in continuous diffusion and flow-based language models (LMs) have achieved performance competitive with discrete LMs. However, existing continuous frameworks still…
Provable diffusion-based posterior sampling for linear inverse problems via DDIM
Yuchen Jiao, Na Li, Changxiao Cai +2
Diffusion-based methods have achieved remarkable empirical success in solving inverse problems. However, many existing posterior samplers either lack rigorous theoretical guarantee…
Diffusion Models Adapt to Low-Dimensional Structure Under Flexible Coefficient Choices
Changxiao Cai, Yuchen Jiao, Gen Li
Diffusion models are known to exploit unknown low-dimensional structure to accelerate sampling. However, existing convergence theory under low-dimensional data structure has largel…
Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions
Jingda Wu, Changxiao Cai
Score-based diffusion models have demonstrated remarkable empirical success in learning high-dimensional distributions, particularly those exhibiting low-dimensional and multi-moda…
Confidence-Based Decoding is Provably Efficient for Diffusion Language Models
Changxiao Cai, Gen Li
Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) models for language modeling, allowing flexible generation order and parallel genera…
Adaptation to Intrinsic Dependence in Diffusion Language Models
Yunxiao Zhao, Changxiao Cai
Diffusion language models (DLMs) have recently emerged as a promising alternative to autoregressive (AR) approaches, enabling parallel token generation beyond a rigid left-to-right…
Are First-Order Diffusion Samplers Really Slower? A Fast Forward-Value Approach
Yuchen Jiao, Na Li, Changxiao Cai +1
Higher-order ODE solvers have become a standard tool for accelerating diffusion probabilistic model (DPM) sampling, motivating the widespread view that first-order methods are inhe…
Breaking AR's Sampling Bottleneck: Provable Acceleration via Diffusion Language Models
Gen Li, Changxiao Cai
Diffusion models have emerged as a powerful paradigm for modern generative modeling, demonstrating strong potential for large language models (LLMs). Unlike conventional autoregres…
Dimension-Free Convergence of Diffusion Models for Approximate Gaussian Mixtures
Gen Li, Changxiao Cai, Yuting Wei
Diffusion models are distinguished by their exceptional generative performance, particularly in producing high-quality samples through iterative denoising. While current theory sug…
Minimax Optimality of the Probability Flow ODE for Diffusion Models
Changxiao Cai, Gen Li
Score-based diffusion models have become a foundational paradigm for modern generative modeling, demonstrating exceptional capability in generating samples from complex high-dimens…
Minimax-optimal trust-aware multi-armed bandits
Changxiao Cai, Jiacheng Zhang
Multi-armed bandit (MAB) algorithms have achieved significant success in sequential decision-making applications, under the premise that humans perfectly implement the recommended…
Provable Acceleration for Diffusion Models under Minimal Assumptions
Gen Li, Changxiao Cai
Score-based diffusion models, while achieving minimax optimality for sampling, are often hampered by slow sampling speeds due to the high computational burden of score function eva…
Transfer Learning for Contextual Multi-armed Bandits
Changxiao Cai, T. Tony Cai, Hongzhe Li
Motivated by a range of applications, we study in this paper the problem of transfer learning for nonparametric contextual multi-armed bandits under the covariate shift model, wher…
Minimax Estimation of Linear Functions of Eigenvectors in the Face of Small Eigen-Gaps
Gen Li, Changxiao Cai, H. Vincent Poor +1
Eigenvector perturbation analysis plays a vital role in various data science applications. A large body of prior works, however, focused on establishing eigenvector pert…
Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis
Gen Li, Changxiao Cai, Yuxin Chen +2
Q-learning, which seeks to learn the optimal Q-function of a Markov decision process (MDP) in a model-free fashion, lies at the heart of reinforcement learning. When it comes to th…
Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality
Changxiao Cai, H. Vincent Poor, Yuxin Chen
We study the distribution and uncertainty of nonconvex optimization for noisy tensor completion -- the problem of estimating a low-rank tensor given incomplete and corrupted observ…
Nonconvex Low-Rank Tensor Completion from Noisy Data
Changxiao Cai, Gen Li, H. Vincent Poor +1
We study a noisy tensor completion problem of broad practical interest, namely, the reconstruction of a low-rank tensor from highly incomplete and randomly corrupted observations o…
Subspace Estimation from Unbalanced and Incomplete Data Matrices: Statistical Guarantees
Changxiao Cai, Gen Li, Yuejie Chi +2
This paper is concerned with estimating the column space of an unknown low-rank matrix , given noisy and partial observatio…
The coordinate transformation and the exact solutions of the Schrödinger equation with position-dependent effective mass
Guo-Xing Ju, Chang-Ying Cai, Yang Xiang +1
Using the coordinate transformation method, we solve the one-dimensional Schrödinger equation with position-dependent mass(PDM). The explicit expressions for the potentials, energy…