Minimax Optimality of Score-Entropy Discrete Diffusion [paper]

Cholyeon Cho, Yuchen Wu.

Preprint, 2026

Method of Moments Estimation of High-Dimensional Covariance Using a Parametric Model [paper]

Iain M. Johnstone*, Yuchen Wu*, Ran Xie*.

Preprint, 2026

When Does Model Collapse Occur in Structured Interactive Learning? [paper]

Yuchen Wu, Kangjie Zhou, Weijie Su.

Preprint, 2026

On the Robustness of Distribution Support under Diffusion Guidance. [paper]

Ruijia Cao, Yuchen Wu, Nisha Chandramoorthy.

Preprint, 2026

On the Robustness of Langevin Dynamics to Score Function Error. [paper]

Daniel Yiming Cao*, August Y. Chen*, Karthik Sridharan*, Yuchen Wu*.

The 43rd International Conference on Machine Learning (ICML 2026)

Provably Reliable Classifier Guidance via Cross-Entropy Control. [paper]

Sharan Sahu, Arisina Banerjee, Yuchen Wu.

The 40th Annual Conference on Neural Information Processing Systems (Neurips 2026).

Learning to Lead: Incentivizing Strategic Agents in the Dark. [paper]

Yuchen Wu, Xinyi Zhong, Zhuoran Yang.

Preprint, 2025

Stochastic Runge-Kutta Methods: Provable Acceleration of Diffusion Models. [paper]

Yuchen Wu, Yuxin Chen, Yuting Wei.

Minor revision at Journal of the American Statistical Association 2026+

Provably efficient posterior sampling for sparse linear regression via measure decomposition. [paper]

Andrea Montanari*, Yuchen Wu*.

Journal of the American Statistical Association 2026

Theoretical insights for diffusion guidance: a case study for Gaussian mixture models. [paper]

Yuchen Wu, Minshuo Chen, Zihao Li, Mengdi Wang, Yuting Wei.

The 41st International Conference on Machine Learning (ICML 2024).

Failures and successes of cross-validation for early-stopped gradient descent in high-dimensional least squares. [paper]

Pratik Patil*, Yuchen Wu*, Ryan Tibshirani.

The 27th International Conference on Artificial Intelligence and Statistics (AISTATS 2024, Oral, top 7.3% of accepted papers).

Sharp analysis of power iteration for tensor PCA. [paper]

Yuchen Wu*, Kangjie Zhou*.

Journal of Machine Learning Research (2024).

Deep networks as denoising algorithms: sample-efficient learning of diffusion models in high-dimensional graphical models. [paper]

Song Mei*, Yuchen Wu*.

IEEE Transactions on Information Theory (2025)

Posterior sampling from the spiked models via diffusion processes. [paper]

Andrea Montanari*, Yuchen Wu*.

Preprint, 2023.

Integrating water quality data with a Bayesian network model to improve spatial and temporal phosphorus attribution: Application to the Maumee River Basin. [paper]

Zihan Wei, Sarfaraz Alam, Miki Verma, Margaret Hilderbran, Yuchen Wu, Brandon Anderson, Daniel E Ho, Jenny Suckale.

Journal of Environmental Management (2024).

Lower bounds for the convergence of tensor power iteration on random overcomplete models. [paper]

Yuchen Wu*, Kangjie Zhou*.

The 36th Annual Conference on Learning Theory (COLT 2023).

Fundamental limits of low-rank matrix estimation with diverging aspect ratios. [paper]

Andrea Montanari*, Yuchen Wu*.

Annals of Statistics (2024).

Adversarial examples in random neural networks with general activations. [paper]

Andrea Montanari*, Yuchen Wu*.

Mathematical Statistics and Learning (2023).

Statistically optimal first order algorithms: a proof via orthogonalization. [paper]

Andrea Montanari*, Yuchen Wu*.

Information and Inference: A Journal of the IMA (2024).

Streaming belief propagation for community detection. [paper]

Yuchen Wu, Jakab Tardos, MohammadHossein Bateni, André Linhares, Filipe Miguel Goncalves de Almeida, Andrea Montanari, Ashkan Norouzi-Fard.

Advances in Neural Information Processing Systems 34 (NeurIPS 2021).

The estimation error of general first order methods. [paper]

Michael Celentano*, Andrea Montanari*, Yuchen Wu*.

The 33rd Annual Conference on Learning Theory (COLT 2020).