Research (by topic)

Learning in the space of probability measures

• Learning Gaussian Mixtures Using the Wasserstein-Fisher-Rao Gradient Flow
  Yuling Yan*, Kaizheng Wang*, Philippe Rigollet (*=equal contribution)
  To appear in Annals of Statistics, 2024
  

• Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
  Gen Li*, Yuling Yan* (*=equal contribution)
  arXiv preprint arXiv:2405.14861, 2024
  

Key words: optimal transport, Wasserstein(-Fisher-Rao) gradient flow, nonparametric MLE, diffusion models

Inference and uncertainty quantification for low-rank models

• Inference and Uncertainty Quantification for Noisy Matrix Completion
  Yuxin Chen, Jianqing Fan, Cong Ma, Yuling Yan (alphabetical order)
  Proceedings of the National Academy of Sciences, vol. 116, no. 46, pp. 22931-22937, 2019
  

• Inference for Heteroskedastic PCA with Missing Data
  Yuling Yan, Yuxin Chen, Jianqing Fan
  Annals of Statistics, vol. 52, no. 2, pp. 729–756, 2024
  

• Entrywise Inference for Causal Panel Data: A Simple and Instance-Optimal Approach
  Yuling Yan, Martin J. Wainwright
  arXiv preprint arXiv:2401.13665, 2024
  

• When Can Weak Latent Factors Be Statistically Inferred?
  Yuheng Zheng, Yuling Yan, Jianqing Fan (alphabetical order)
  arXiv preprint arXiv:2407.03616, 2024
  

Key words: entrywise confidence intervals, optimization methods, spectral methods, optimality, matrix completion, PCA, causal panel data

Optimization methods for statistical estimation

• Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization
  Yuxin Chen, Yuejie Chi, Jianqing Fan, Cong Ma, Yuling Yan (alphabetical order)
  SIAM Journal on Optimization, vol. 30, no. 4, pp. 3098-3121, 2020
  

• Bridging Convex and Nonconvex Optimization in Robust PCA: Noise, Outliers, and Missing Data
  Yuxin Chen, Jianqing Fan, Cong Ma, Yuling Yan (alphabetical order)
  Annals of Statistics, vol. 49, no. 5, pp. 2948-2971, 2021
  

• Convex and Nonconvex Optimization Are Both Minimax-Optimal for Noisy Blind Deconvolution
  Yuxin Chen, Jianqing Fan, Bingyan Wang, Yuling Yan (alphabetical order)
  Journal of the American Statistical Association, vol. 118, no. 542, pp. 858-868, 2023
  

• Efficient Clustering for Stretched Mixtures: Landscape and Optimality
  Kaizheng Wang, Yuling Yan, Mateo Díaz
  Neural Information Processing Systems (NeurIPS), 2020
  

Key words: nonconvex optimization, convex relaxation, optimality, matrix completion, robust PCA, clustering

Applications to economics and social sciences

• The Isotonic Mechanism for Exponential Family Estimation
  Yuling Yan, Weijie J. Su, Jianqing Fan
  arXiv preprint arXiv:2304.11160, under major revision at Journal of the Royal Statistical Society: Series B
  

• Analysis of the ICML 2023 Ranking Data: Can Authors’ Opinions of Their Own Papers Assist Peer Review in Machine Learning?
  Buxin Su, Jiayao Zhang, Natalie Collina, Yuling Yan, Didong Li, Kyunghyun Cho, Jianqing Fan, Aaron Roth, Weijie J. Su
  arXiv preprint arXiv:2408.13430
  

• Asymptotic Seed Bias in Respondent-driven Sampling
  Yuling Yan, Bret Hanlon, Sebastien Roch, Karl Rohe
  Electronic Journal of Statistics, vol. 14, no. 1, pp. 1577-1610, 2020
  

Key words: mechanism design, causal inference, public policy

Statistical reinforcement learning and decision making

• Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model
  Bingyan Wang*, Yuling Yan*, Jianqing Fan (*=equal contribution)
  Neural Information Processing Systems (NeurIPS), 2021
  

• The Efficacy of Pessimism in Asynchronous Q-learning
  Yuling Yan, Gen Li, Yuxin Chen, Jianqing Fan
  IEEE Transactions on Information Theory, vol. 69, no. 11, pp. 7185-7219, 2023
  

• Model-Based Reinforcement Learning Is Minimax-Optimal for Offline Zero-Sum Markov Games
  Yuling Yan, Gen Li, Yuxin Chen, Jianqing Fan
  To appear in Operations Research, 2024
  

• Minimax-Optimal Reward-Agnostic Exploration in Reinforcement Learning
  Gen Li, Yuling Yan, Yuxin Chen, Jianqing Fan
  arXiv preprint arXiv:2304.07278, 2023, accepted in part to Conference on Learning Theory (COLT), 2024
  

Key words: offline RL, multi-agent RL, sample complexity, optimality