Will Fithian is an Associate Professor in the Department of Statistics at the University of California, Berkeley, with his office in Evans Hall #301. He earned his Ph.D. in Statistics from Stanford University in 2015, where his dissertation "Topics in Adaptive Inference" was advised by Trevor Hastie and included committee members Emmanuel Candès, Jonathan Taylor, and Robert Tibshirani. While at Stanford, Fithian taught Stat 200: Introduction to Statistical Inference (Winter 2013), Stat 302: Qualifying Exams Workshop (Summer 2013 and 2014), and Stat 390: Consulting Workshop (Spring 2015). He received the Statistics Department Teaching Award in June 2012 and the university-wide Centennial Teaching Award in June 2015. Since joining UC Berkeley, he has taught Stat 210A: Theoretical Statistics (Fall 2016-2021 and Fall 2025), Stat 212A: Topics in Selective Inference (Fall 2015), Stat 28: Statistical Methods for Data Science (Spring 2018), Data 8: Foundations of Data Science (Spring 2019), and an Applied Statistics Seminar on Statistical Methods for Species Distributions and Abundances (Fall 2019).

Fithian's research interests include post-selection inference and selective inference, scalable statistical inference for massive data, statistical machine learning, high-dimensional statistics, multiple testing, optimization and statistical computing, multivariate analysis and dimensionality reduction in large datasets, methods for stable estimation and inference in heavy-tailed data, and ecological statistics. Key contributions include AdaPT-GMM for powerful and robust covariate-assisted multiple testing, BONuS for multiple multivariate testing with data-adaptive test statistics, STAR as a general interactive framework for FDR control under structural constraints, and AdaPT as an interactive procedure for multiple testing with side information. Notable publications are "AdaPT: An interactive procedure for multiple testing with side information" with Lihua Lei (Journal of the Royal Statistical Society: Series B, 2018), "STAR: A general interactive framework for FDR control under structural constraints" with Lihua Lei and Aaditya Ramdas (Biometrika, 2020), "Conditional calibration for false discovery rate control under dependence" with Lihua Lei (Annals of Statistics, 2022), "Optimal Inference After Model Selection" with Dennis Sun and Jonathan Taylor (2014), "Local Case-Control Sampling: Efficient Subsampling in Imbalanced Data Sets" with Trevor Hastie (Annals of Statistics, 2014), "Selection Adjusted Confidence Intervals with More Power to Determine the Sign" with Asaf Weinstein and Yoav Benjamini (Journal of the American Statistical Association, 2012), and "Scalable Convex Methods for Flexible Low-Rank Matrix Modeling" with Rahul Mazumder (Statistical Science, 2018). He develops R packages such as multispeciesPP and selectiveInference.

Professional Email: wfithian@berkeley.edu