One of the beauties of the projected gradient descent method lies in its rather simple
mechanism and yet stable behavior with inexact, stochastic gradients, which has led to its …

Submodular maximization under various constraints is a fundamental problem studied
continuously, in both computer science and operations research, since the late 1970's. A …

In recent years, maximization of DR-submodular continuous functions became an important
research field, with many real-worlds applications in the domains of machine learning …

We investigate the online bandit learning of the monotone multi-linear DR-submodular
functions, designing the algorithm $\mathtt {BanditMLSM} $ that attains $ O (T^{2/3}\log T) …

Motivated by online decision-making in time-varying combinatorial environments, we study
the problem of transforming offline algorithms to their online counterparts. We focus on …

This paper presents a unified approach for maximizing continuous DR-submodular functions
that encompasses a range of settings and oracle access types. Our approach includes a …

Mean field inference for discrete graphical models is generally a highly nonconvex problem,
which also holds for the class of probabilistic log-submodular models. Existing optimization …

In this paper, we revisit the online non-monotone continuous DR-submodular maximization
problem over a down-closed convex set, which finds wide real-world applications in the …

Maximizing a DR-submodular function subject to a general convex set is an NP-hard
problem arising from many applications in combinatorial optimization and machine learning …

It has been well established that first order optimization methods can converge to the
maximal objective value of concave functions and provide constant factor approximation …