72 citations · 231 across the 61 of their papers we have counts for
5 papers · 1 filter
High-dimensional Berry-Esseen Bound for -Dependent Random Samples
Heejong Bong, Arun Kumar Kuchibhotla, Alessandro Rinaldo
In this work, we provide a -rate finite sample Berry-Esseen bound for -dependent high-dimensional random vectors over the class of hyper-rectangles. This bound imp…
Bagging in overparameterized learning: Risk characterization and risk monotonization
Pratik Patil, Jin-Hong Du, Arun Kumar Kuchibhotla
Bagging is a commonly used ensemble technique in statistics and machine learning to improve the performance of prediction procedures. In this paper, we study the prediction risk of…
Median Regularity and Honest Inference
Arun Kumar Kuchibhotla, Sivaraman Balakrishnan, Larry Wasserman
We introduce a new notion of regularity of an estimator called median regularity. We prove that uniformly valid (honest) inference for a functional is possible if and only if there…
Mitigating multiple descents: A model-agnostic framework for risk monotonization
Pratik Patil, Arun Kumar Kuchibhotla, Yuting Wei +1
Recent empirical and theoretical analyses of several commonly used prediction procedures reveal a peculiar risk behavior in high dimensions, referred to as double/multiple descent,…
Doubly Robust Calibration of Prediction Sets under Covariate Shift
Yachong Yang, Arun Kumar Kuchibhotla, Eric Tchetgen Tchetgen
Conformal prediction has received tremendous attention in recent years and has offered new solutions to problems in missing data and causal inference; yet these advances have not l…