Harro Walk

collaborators

3 papers

stat.ML2026

On Rate-Optimal Partitioning Classification from Observable and from Privatised Data

BalÃ¡zs CsanÃ¡d CsÃ¡ji, LÃ¡szlÃ³ GyÃ¶rfi, Ambrus TamÃ¡s +1

In this paper we revisit the classical method of partitioning classification and prove novel convergence rates under relaxed conditions, both for observable (non-privatised) and fo…

math.ST2026

On public and private binary classification with metric space valued predictors

LÃ¡szlÃ³ GyÃ¶rfi, Martin Kroll, Harro Walk

We consider the problem of binary classification in a framework where the predictor $X$ takes values in an arbitrary separable metric space $X$ and the label $Y$ values in…

math.ST2024

Distribution-free tests for lossless feature selection in classification and regression

LÃ¡szlÃ³ GyÃ¶rfi, TamÃ¡s Linder, Harro Walk

We study the problem of lossless feature selection for a $d$ -dimensional feature vector $X = (X^{(1)}, \dots, X^{(d)})$ and label $Y$ for binary classification as well as nonparametri…