6 papers
Honest Inference for Stochastic Optimization
Kenta Takatsu, Arun Kumar Kuchibhotla
This manuscript studies a general approach to construct confidence sets for the solution of stochastic optimization, rendering empirical risk minimization as special cases. Statist…
From Isotonic to Lipschitz Regression: A New Interpolative Perspective on Shape-restricted Estimation
Kenta Takatsu, Tianyu Zhang, Arun Kumar Kuchibhotla
This manuscript bridges nonparametric smoothness-based and shape-restricted estimation, which may appear as two disjoint paradigms in the field. The proposed approach is motivated…
Learning from Discriminatory Training Data
Przemyslaw A. Grabowicz, Nicholas Perello, Kenta Takatsu
Supervised learning systems are trained using historical data and, if the data was tainted by discrimination, they may unintentionally learn to discriminate against protected group…
On the Precise Asymptotics of Universal Inference
Kenta Takatsu
In statistical inference, confidence set procedures are typically evaluated based on their validity and width properties. Even when procedures achieve rate-optimal widths, confiden…
The Berry-Esseen Bound for High-dimensional Self-normalized Sums
Woonyoung Chang, Kenta Takatsu, Konrad Urban +1
This manuscript studies the Gaussian approximation of the coordinate-wise maximum of self-normalized statistics in high-dimensional settings. We derive an explicit Berry-Esseen bou…
Generalized van Trees inequality: Local minimax bounds for non-smooth functionals and irregular statistical models
Kenta Takatsu, Arun Kumar Kuchibhotla
In a decision-theoretic framework, the minimax lower bound provides the worst-case performance of estimators relative to a given class of statistical models. For parametric and sem…