KATRA, Oct 10: School of Mathematics, SMVDU, Katra, organized a guest lecture on "The Descent of Learning: Gradient-Based Optimization from Cauchy to Contemporary Data Science". The lecture was ...
We introduce a new Swarm-Based Descent (SBD) method for non-convex optimization. The swarm consists of agents, each identified with position, x, and mass, m. There are three key aspects to the SBD ...