Improved deterministic online algorithms color k-colorable graphs with O(n to the power of 1 minus 1 over k(k-1)/2) colors for k at least 5 and O(n to the 14/17) for k=4, plus a randomized bound for bipartite graphs that narrows the gap to a factor of 1.09.
The nonstochastic multiarmed bandit problem.SIAM journal on computing, 32(1):48–77, 2002
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Prudent-Banker achieves pseudo-regret Õ(√T + √D) and Õ(1) regret vs. safe comparator in adversarial bandits both with and without delays, matching new lower bounds up to logs.
citing papers explorer
-
Online Graph Coloring for $k$-Colorable Graphs
Improved deterministic online algorithms color k-colorable graphs with O(n to the power of 1 minus 1 over k(k-1)/2) colors for k at least 5 and O(n to the 14/17) for k=4, plus a randomized bound for bipartite graphs that narrows the gap to a factor of 1.09.
-
Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays
Prudent-Banker achieves pseudo-regret Õ(√T + √D) and Õ(1) regret vs. safe comparator in adversarial bandits both with and without delays, matching new lower bounds up to logs.