Bandits With Heavy Tail

DOI10.1109/TIT.2013.2277869zbMath1364.62213arXiv1209.1727OpenAlexW1984332158WikidataQ59538557 ScholiaQ59538557MaRDI QIDQ5346276

Nicolò Cesa-Bianchi, Sébastien Bubeck, Gábor Lugosi

Publication date: 8 June 2017

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1209.1727

Mathematics Subject Classification ID

Robustness and adaptive procedures (parametric inference) (62F35) Sequential statistical analysis (62L10) General considerations in statistical decision theory (62C05)

Related Items (24)

Robust sub-Gaussian estimation of a mean vector in nearly linear time ⋮ Best Arm Identification for Contaminated Bandits ⋮ The robust nearest shrunken centroids classifier for high-dimensional heavy-tailed data ⋮ Robust estimation of \(U\)-statistics ⋮ Median-of-means approach for repeated measures data ⋮ Empirical risk minimization for heavy-tailed losses ⋮ Rate-optimal robust estimation of high-dimensional vector autoregressive models ⋮ Unnamed Item ⋮ Catoni-style confidence sequences for heavy-tailed mean estimation ⋮ Robust supervised learning with coordinate gradient descent ⋮ Finite-Time Analysis for the Knowledge-Gradient Policy ⋮ Corruption-tolerant bandit learning ⋮ Filtered Poisson process bandit on a continuum ⋮ Solvable integration problems and optimal sample size selection ⋮ Geometric median and robust estimation in Banach spaces ⋮ Distributed statistical estimation and rates of convergence in normal approximation ⋮ Adaptive policies for perimeter surveillance problems ⋮ Algorithms of robust stochastic optimization based on mirror descent method ⋮ Multi-armed bandit with sub-exponential rewards ⋮ Convergence rates of least squares regression estimators with heavy-tailed errors ⋮ A generalized Catoni's M-estimator under finite \(\alpha\)-th moment assumption with \(\alpha \in (1,2)\) ⋮ Scale calibration for high-dimensional robust regression ⋮ Robust parameter estimation of regression models under weakened moment assumptions ⋮ Mean estimation and regression under heavy-tailed distributions: A survey

This page was built for publication: Bandits With Heavy Tail