Gradient-based methods have been widely used for system design and optimization in
diverse application domains. Recently, there has been a renewed interest in studying …

In many optimization problems arising from scientific, engineering and artificial intelligence
applications, objective and constraint functions are available only as the output of a black …

Nonsmooth nonconvex optimization problems broadly emerge in machine learning and
business decision making, whereas two core challenges impede the development of …

The empirical success of reinforcement learning (RL) in contact-rich manipulation leaves
much to be understood from a model-based perspective, where the key difficulties are often …

We provide the first non-asymptotic analysis for finding stationary points of nonsmooth,
nonconvex functions. In particular, we study the class of Hadamard semi-differentiable …

We study the complexity of optimizing nonsmooth nonconvex Lipschitz functions by
producing $(\delta,\epsilon) $-Goldstein stationary points. Several recent works have …

The empirical success of derivative-free methods in reinforcement learning for planning
through contact seems at odds with the perceived fragility of classical gradient-based …

Abstract Zhang et al.(ICML 2020) introduced a novel modification of Goldstein's classical
subgradient method, with an efficiency guarantee of $ O (\varepsilon^{-4}) $ for minimizing …

The applications of direct policy search in reinforcement learning and continuous control
have received increasing attention. In this work, we present novel theoretical results on the …

We report a practical finite-time algorithmic scheme to compute approximately stationary
points for nonconvex nonsmooth Lipschitz functions. In particular, we are interested in two …