New UCB algorithms resist contamination in bandit problems.
problem Stochastic bandit problems with ε-contaminated rewards.
method Robust mean estimators and crUCB algorithms.
result Achieves O(√KTlogT) regret for small contamination proportions.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
2 results for “crUCB”
CRB tackles rising rewards in combinatorial online learning.
problem Rising rewards in combinatorial online learning.
method CRB framework and CRUCB algorithm.
result Empirical and theoretical validation of CRUCB's effectiveness.