Search Results for author: Arun Kumar Kuchibhotla

Found 10 papers, 1 papers with code

Subsample Ridge Ensembles: Equivalences and Generalized Cross-Validation

no code implementations25 Apr 2023 Jin-Hong Du, Pratik Patil, Arun Kumar Kuchibhotla

We study subsampling-based ridge ensembles in the proportional asymptotics regime, where the feature size grows proportionally with the sample size such that their ratio converges to a constant.

Extrapolated cross-validation for randomized ensembles

no code implementations27 Feb 2023 Jin-Hong Du, Pratik Patil, Kathryn Roeder, Arun Kumar Kuchibhotla

By establishing uniform consistency of our risk extrapolation technique over ensemble and subsample sizes, we show that ECV yields $\delta$-optimal (with respect to the oracle-tuned risk) ensembles for squared prediction risk.

Bagging in overparameterized learning: Risk characterization and risk monotonization

no code implementations20 Oct 2022 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.

Mitigating multiple descents: A model-agnostic framework for risk monotonization

no code implementations25 May 2022 Pratik Patil, Arun Kumar Kuchibhotla, Yuting Wei, Alessandro Rinaldo

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, in which the asymptotic risk is a non-monotonic function of the limiting aspect ratio of the number of features or parameters to the sample size.

Improving Fairness in Criminal Justice Algorithmic Risk Assessments Using Conformal Prediction Sets

no code implementations26 Aug 2020 Richard A. Berk, Arun Kumar Kuchibhotla

Risk assessment algorithms have been correctly criticized for potential unfairness, and there is an active cottage industry trying to make repairs.

Conformal Prediction Fairness +1

Near-Optimal Confidence Sequences for Bounded Random Variables

1 code implementation9 Jun 2020 Arun Kumar Kuchibhotla, Qinqing Zheng

Many inference problems, such as sequential decision problems like A/B testing, adaptive sampling schemes like bandit selection, are often online in nature.

valid

Exchangeability, Conformal Prediction, and Rank Tests

no code implementations13 May 2020 Arun Kumar Kuchibhotla

The concept of exchangeability is also at the core of rank tests widely known in nonparametric statistics.

BIG-bench Machine Learning Conformal Prediction +1

Deterministic Inequalities for Smooth M-estimators

no code implementations13 Sep 2018 Arun Kumar Kuchibhotla

Ever since the proof of asymptotic normality of maximum likelihood estimator by Cramer (1946), it has been understood that a basic technique of the Taylor series expansion suffices for asymptotics of $M$-estimators with smooth/differentiable loss function.

Moving Beyond Sub-Gaussianity in High-Dimensional Statistics: Applications in Covariance Estimation and Linear Regression

no code implementations8 Apr 2018 Arun Kumar Kuchibhotla, Abhishek Chakrabortty

The third example concerns the restricted eigenvalue condition, required in HD linear regression, which we verify for all sub-Weibull random vectors through a unified analysis, and also prove a more general result related to restricted strong convexity in the process.

regression

Cannot find the paper you are looking for? You can Submit a new open access paper.