The history of learning for control has been an exciting back and forth between twobroad classes ofalgorithms: planning andreinforcement learning.

In this section, we provide an open-ended discussion on how the prior distribution ( i.e., imbalanced

We provide a few error-bound results on its convergence rates. Specially, we prove that theSPIDER-SFO algorithm achieves a gradient computation cost of O min(n1/2 2, 3) to find an -approximate first-order stationary point. In addition, we prove thatSPIDER-SFO nearly matches the algorithmic lower bound for finding stationary point under the gradient Lipschitz assumption in the finite-sum setting.

We study a distributionally robust mean square error estimation problem over a nonconvexWasserstein ambiguity set containing only normal distributions.

Bayesian decision theory outlines arigorous framework for making optimal decisions based on maximizing expected utility over a model posterior.

Images taken between 2013 and 2015 are used as the validation set.

In this work, we aim to warm-start BO in the context of hyperparameter optimization (HPO).

The experimental data is used to train complex-weighted models with a range of regularisation approaches.