On stochastic and deterministic quasi-Newton methods for non-Strongly convex optimization: Asymptotic convergence and rate analysis

no code implementations • 16 Oct 2017 • Farzad Yousefian, Angelia Nedić, Uday Shanbhag

To the best of our knowledge, no rate statements currently exist for SQN methods in the absence of such an assumption.

Optimization and Control

Stochastic quasi-Newton methods for non-strongly convex problems: convergence and rate analysis

no code implementations • 15 Mar 2016 • Farzad Yousefian, Angelia Nedić, Uday V. Shanbha

Moreover, the rate of convergence in terms of the objective function value is derived.

Optimization and Control

A distributed adaptive steplength stochastic approximation method for monotone stochastic Nash Games

no code implementations • 19 Mar 2013 • Farzad Yousefian, Angelia Nedich, Uday V. Shanbhag

While a centralized adaptive stepsize SA scheme is proposed in [1] for the optimization framework, such a scheme provides no freedom for the agents in choosing their own stepsizes.

Optimization and Control