Reinforcement learning is about learning agent models that make the best sequential
decisions in unknown environments. In an unknown environment, the agent needs to …

Optimizing deep neural networks (DNNs) running on resource-constrained devices, such as
energy harvesting sensor devices, poses unique challenges due to the limited memory and …

In this paper, we consider a stochastic distributed nonconvex optimization problem with the
cost function being distributed over n agents having access only to zeroth-order (ZO) …

Silicon-photonics-based optical neural network (ONN) is a promising hardware platform that
could represent a paradigm shift in efficient AI with its CMOS-compatibility, flexibility, ultra …

Optical neural networks (ONNs) have demonstrated record-breaking potential in high-
performance neuromorphic computing due to their ultra-high execution speed and low …

Backward propagation (BP) is widely used to compute the gradients in neural network
training. However, it is hard to implement BP on edge devices due to the lack of hardware …

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

We present a new zero-order optimization method called Minibatch Stochastic Three Points
(MiSTP), specifically designed to solve stochastic unconstrained minimization problems …

Derivative-free optimization problems are optimization problems where derivative
information is unavailable. The least Frobenius norm updating quadratic interpolation model …

Direct search methods are a class of popular global optimization algorithms for general
nonconvex programs. In this paper, we propose a randomized directional search algorithm …