Person
Bousquet
A researcher who, together with Warmuth, studied the problem of online learning over a discrete set of experts and in 2020 proposed an efficient algorithm achieving the information-theoretic lower bound.
Timeline (last 90 days)
Oct 15
In 2020, Bousquet and Warmuth gave an efficient algorithm for a discrete set of experts, whose regret reaches the information-theoretic lower bound, that is, when the comparator switches k times among m experts, the regret is Õ(md+k), and the computation is polynomial-time.
Unverified50%