Concept
Robbins-Monro Conditions
Classical sufficient conditions in stochastic approximation theory that guarantee the convergence of iterative procedures. They require the step-size sequence to satisfy divergence of the series of step sizes and convergence of the series of their squares.
Timeline (last 90 days)
Oct 14
Classical stochastic approximation theory relies on the Robbins-Monro conditions to guarantee convergence, but SGDM with a constant step size does not satisfy these conditions, and the parameters keep fluctuating around a steady state rather than converging to a point.
Unverified50%