all AI news
On Frequentist Regret of Linear Thompson Sampling. (arXiv:2006.06790v3 [cs.LG] UPDATED)
stat.ML updates on arXiv.org arxiv.org
This paper studies the stochastic linear bandit problem, where a
decision-maker chooses actions from possibly time-dependent sets of vectors in
$\mathbb{R}^d$ and receives noisy rewards. The objective is to minimize regret,
the difference between the cumulative expected reward of the decision-maker and
that of an oracle with access to the expected reward of each action, over a
sequence of $T$ decisions. Linear Thompson Sampling (LinTS) is a popular
Bayesian heuristic, supported by theoretical analysis that shows its Bayesian
regret is …
analysis arxiv bayesian decision decisions difference linear minimax oracle paper popular sampling shows stochastic studies vectors