activity
20182020
collaborators

5 papers

math.ST2020

On conditional versus marginal bias in multi-armed bandits

Jaehyeok Shin, Aaditya Ramdas, Alessandro Rinaldo

The bias of the sample means of the arms in multi-armed bandits is an important issue in adaptive data analysis that has recently received considerable attention in the literature.…

math.ST2019

Are sample means in multi-armed bandits positively or negatively biased?

Jaehyeok Shin, Aaditya Ramdas, Alessandro Rinaldo

It is well known that in stochastic multi-armed bandits (MAB), the sample mean of an arm is typically not an unbiased estimator of its true mean. In this paper, we decouple three d…

stat.ME2019

Predictive clustering

Jaehyeok Shin, Alessandro Rinaldo, Larry Wasserman

We show how to convert any clustering into a prediction set. This has the effect of converting the clustering into a (possibly overlapping) union of spheres or ellipsoids. The tuni…

math.AT2019

Homotopy Reconstruction via the Cech Complex and the Vietoris-Rips Complex

Jisu Kim, Jaehyeok Shin, Frédéric Chazal +2

We derive conditions under which the reconstruction of a target space is topologically correct via the Čech complex or the Vietoris-Rips complex obtained from possibly noisy point…

math.ST2018

Uniform Convergence Rate of the Kernel Density Estimator Adaptive to Intrinsic Volume Dimension

Jisu Kim, Jaehyeok Shin, Alessandro Rinaldo +1

We derive concentration inequalities for the supremum norm of the difference between a kernel density estimator (KDE) and its point-wise expectation that hold uniformly over the se…