303 citations · 325 across the 5 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2012★ 303 cited
Further Optimal Regret Bounds for Thompson Sampling
Shipra Agrawal, Navin Goyal
Thompson Sampling is one of the oldest heuristics for multi-armed bandit problems. It is a randomized algorithm based on Bayesian ideas, and has recently generated significant inte…
cs.LG2009★ 20 cited
Learning convex bodies is hard
Navin Goyal, Luis Rademacher
We show that learning a convex body in $\RR^d$, given random samples from the body, requires $2^{Ω(\sqrt{d/\eps})}$ samples. By learning a convex body we mean finding a set having…