pith. sign in

arxiv: 1712.04104 · v3 · pith:5NWPJ73Mnew · submitted 2017-12-12 · 🧮 math.OC · cs.LG

Convergence Rates for Deterministic and Stochastic Subgradient Methods Without Lipschitz Continuity

classification 🧮 math.OC cs.LG
keywords convergencesubgradientfunctionslipschitzrateclassicconvexdeterministic
0
0 comments X
read the original abstract

We extend the classic convergence rate theory for subgradient methods to apply to non-Lipschitz functions. For the deterministic projected subgradient method, we present a global $O(1/\sqrt{T})$ convergence rate for any convex function which is locally Lipschitz around its minimizers. This approach is based on Shor's classic subgradient analysis and implies generalizations of the standard convergence rates for gradient descent on functions with Lipschitz or H\"older continuous gradients. Further, we show a $O(1/\sqrt{T})$ convergence rate for the stochastic projected subgradient method on convex functions with at most quadratic growth, which improves to $O(1/T)$ under either strong convexity or a weaker quadratic lower bound condition.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.