In this paper, we propose and analyze zeroth-order stochastic approximation algorithms for nonconvex convex optimization, with a focus on addressing constrained high-dimensional setting, saddle point avoiding. To handle first generalizations of the conditional gradient algorithm achieving rates similar to standard using only information. facilitate optimization in high dimensions, explore advan...

A wideband on-body antenna for a wireless body area network for an Industrial, Scientific, and Medical band is proposed. A wideband characteristic is achieved by combining two zeroth-order resonance (ZOR) modes at adjacent frequencies by controlling the value of the shunt capacitance. The size of the proposed antenna is 0.072λ0 × 0.33λ0, and the measured 10-dB return loss bandwidth is 340 MHz (...

We consider the problem of global optimization of an unknown non-convex smooth function with zeroth-order feedback. In this setup, an algorithm is allowed to adaptively query the underlying function at different locations and receives noisy evaluations of function values at the queried points (i.e. the algorithm has access to zeroth-order information). Optimization performance is evaluated by t...