Regret Bounds for Deterministic Gaussian Process Bandits
share
This paper analyses the problem of Gaussian process (GP) bandits with deterministic observations. The analysis uses a branch and bound algorithm that is related to the UCB algorithm of (Srinivas et al., 2010). For GPs with Gaussian observation noise, with variance strictly greater than zero, (Srinivas et al., 2010) proved that the regret vanishes at the approximate rate of O(1/√(t)), where t is the number of observations. To complement their result, we attack the deterministic case and attain a much faster exponential convergence rate. Under some regularity assumptions, we show that the regret decreases asymptotically according to O(e^-τ t/( t)^d/4) with high probability. Here, d is the dimension of the search space and τ is a constant that depends on the behaviour of the objective function near its global maximum.
READ FULL TEXT