Bayesian optimization has emerged at the forefront of expensive black-box optimization due
to its data efficiency. Recent years have witnessed a proliferation of studies on the …

We propose a general random subspace framework for unconstrained nonconvex
optimization problems that requires a weak probabilistic assumption on the subspace …

We introduce the class of SO-friendly neural networks, which include several models used in
practice including networks with 2 layers of hidden weights where the number of inputs is …

Bayesian optimization relies on iteratively constructing and optimizing an acquisition
function. The latter turns out to be a challenging, non-convex optimization problem itself …

While there already exist randomized subspace Newton methods that restrict the search
direction to a random subspace for a convex function, we propose a randomized subspace …

The paper discusses derivative-free optimization (DFO), which involves minimizing a
function without access to gradients or directional derivatives, only function evaluations …

This paper integrates manifold learning techniques within a Gaussian process upper
confidence bound algorithm to optimize an objective function on a manifold. Our approach is …

Many problems in science and technology require finding global minima or maxima of
complicated objective functions. The importance of global optimization has inspired the …

One way to solve very large linear programs in standard form is to apply a random projection
to the constraints, then solve the projected linear program. This will yield a guaranteed …

We propose an algorithmic framework, that employs active subspace techniques, for
scalable global optimization of functions with low effective dimension (also referred to as low …