Yihong Wu

Research interests

I am broadly interested in the theoretical and algorithmic aspects of high-dimensional statistics, information theory, and optimization.

Recent papers

• Andre Wibisono, Yihong Wu, Kaylee Yingxi Yang, "Optimal score estimation via empirical Bayes smoothing", Feb 2024.

• Leon Lufkin, Yihong Wu, Jiaming Xu, "Sharp Information-Theoretic Thresholds for Shuffled Linear Regression", Feb 2024.

• Zhou Fan, Leying Guan, Yandi Shen, Yihong Wu, "Gradient flows for empirical Bayes in high-dimensional linear models", Dec 2023.

• Soham Jana, Yury Polyanskiy, Anzo Teh, and Yihong Wu, "Empirical Bayes via ERM and Rademacher complexities: the Poisson model", Conference on Learning Theory (COLT), 2023.

• Zeyu Jia, Yury Polyanskiy, and Yihong Wu, "Entropic characterization of optimal rates for learning Gaussian mixtures", Conference on Learning Theory (COLT), 2023.

• Yun Ma, Yihong Wu, and Pengkun Yang, "On the best approximation by finite Gaussian mixtures", 2023 IEEE International Symposium on Information Theory (ISIT), 2023, pp. 2619–2624.

• Yutong Nie and Yihong Wu, "Large-scale multiple testing: Fundamental limits of false discovery rate control and compound oracle?", Feb 2023.

• Yandi Shen and Yihong Wu, "Empirical Bayes estimation: When does -modeling beat -modeling in theory (and in practice)?", Nov 2022.