3 papers
cs.LG2024
Data-Driven Upper Confidence Bounds with Near-Optimal Regret for Heavy-Tailed Bandits
Ambrus Tamás, Szabolcs Szentpéteri, Balázs Csanád Csáji
Stochastic multi-armed bandits (MABs) provide a fundamental reinforcement learning model to study sequential decision making in uncertain environments. The upper confidence bounds…
stat.ML2023
On Rate-Optimal Partitioning Classification from Observable and from Privatised Data
Balázs Csanád Csáji, László Györfi, Ambrus Tamás +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…
stat.ML2023
Resampled Confidence Regions with Exponential Shrinkage for the Regression Function of Binary Classification
Ambrus Tamás, Balázs Csanád Csáji
The regression function is one of the key objects of binary classification, since it not only determines a Bayes optimal classifier, hence, defines an optimal decision boundary, bu…