2023年11月4日，清华大学统计学博士生论坛成功举办。该活动是清华大学统计学研究中心的传统活动，其设立的目标是为青年统计学者提供学术交流和分享的平台，以提高统计学者的专业知识及专业素养。同学们的科研方向涵盖统计理论基础研究、数据分析方法等多个方面，针对各自的研究成果和科研动态进行全方位展示。
俞老师提到，统计学者们需要保持脚踏实地的态度，既要深入理论研究，又要紧密结合实际问题，为社会和行业提供有力的解决方案。统计学的魅力在于它不仅是一门严密的理论体系，更是解决现实问题的重要工具，它能帮助我们更好地理解复杂的数据背后隐藏的规律，为决策提供科学依据。俞老师鼓励青年学者们不仅要在学术研究上精益求精，还要保持对实际问题的敏感性，积极参与到社会的发展和进步中去。
博士生论坛风采
Generalization error curves of analytic spectral algorithms over hilbert spaces under power-law decay
Debiased regression adjustment in completely randomized experiments with moderately high-dimensional covariates
PMC-patients, a large-scale dataset of patient summaries for retrieval-based clinical decision support systems
High-dimensional statistics multi-group quadratic discriminant analysis via projection
Rerandomization criteria of 2K factorial design–taking the importance of covariates and factorial effects into consideration
On the best approximation by finite Gaussian mixtures
Chasing the heat: unraveling urban hyperlocal air temperature mapping with mobile sensing and statistical methods
TopWORDS-relation: extracting relations from domain-specific chinese texts via a relational dual-dictionary model
Optimal rate of kernel regression in large dimensions
Optimal rates of kernel ridge regression under source condition in large dimensions
HEAT-CF: Inference of heterogeneous perturbation effects in single-cell CRISPR screening experiments at single cell resolution
On the optimality of sliced average variance estimate in high dimensions
Simultaneous inference for mean function of partially observed functional data
Inference for ARMA time series with mildly-varying trend
Simultaneous inference for monotone and smoothly time varying functions under complex temporal dynamics
Testing conditional quantile independence with functional covariate
Treatment effect estimation under covariate-adaptive randomization with heavy-tailed outcome
