Convergence of a Stochastic Gradient Method with Momentum for Non-Smooth Non-Convex Optimization
This provides theoretical guarantees for widely used optimization methods in machine learning, addressing a gap for non-smooth and non-convex problems.
The paper tackles the problem of establishing convergence rates for stochastic gradient methods with momentum in non-smooth, non-convex, and constrained optimization, achieving a proven complexity bound without tuning the momentum parameter.
Stochastic gradient methods with momentum are widely used in applications and at the core of optimization subroutines in many popular machine learning libraries. However, their sample complexities have not been obtained for problems beyond those that are convex or smooth. This paper establishes the convergence rate of a stochastic subgradient method with a momentum term of Polyak type for a broad class of non-smooth, non-convex, and constrained optimization problems. Our key innovation is the construction of a special Lyapunov function for which the proven complexity can be achieved without any tuning of the momentum parameter. For smooth problems, we extend the known complexity bound to the constrained case and demonstrate how the unconstrained case can be analyzed under weaker assumptions than the state-of-the-art. Numerical results confirm our theoretical developments.