We propose a new framework for reasoning about generalization in deep learning. The core
idea is to couple the Real World, where optimizers take stochastic gradient steps on the …

Distributed bandit online convex optimization with time-varying coupled inequality
constraints is considered, motivated by a repeated game between a group of learners and …

We study online optimization in a setting where an online learner seeks to optimize a per-
round hitting cost, which may be non-convex, while incurring a movement cost when …

We investigate online nonconvex optimization from a local regret minimization perspective.
Previous studies along this line implicitly required the access to sufficient gradient oracles at …

Many Internet platforms are information-oriented and crowd-based. They collect fresh
information of various points of interest (PoIs) relying on users who happen to be nearby the …

We study the problem of {\em online} low-rank matrix completion with $\mathsf {M} $ users,
$\mathsf {N} $ items and $\mathsf {T} $ rounds. In each round, the algorithm recommends …

Optimization in the presence of sharp (non-Lipschitz), unpredictable (wrt time and amount)
changes is a challenging and largely unexplored problem of great significance. We consider …

An online majorized semi-proximal alternating direction method of multiplier (Online-
mspADMM) is proposed for a broad class of online linearly constrained composite …

Online nonconvex optimization has been an active area of research recently. Previous
studies either considered the global regret with full information about the objective functions …

Bandit online multiclass prediction plays an important role in many real-world applications.
In this paper, we propose a unified framework for it in the fully adversarial setting. This …