We formulate and study a decentralized multi-armed bandit (MAB) problem. There are distributed players competing for independent arms. Each arm, when played, offers i.i.d. reward a...
Many recognition algorithms depend on careful positioning of an object into a canonical pose, so the position of features relative to a fixed coordinate system can be examined. Cu...
In multi-task learning several related tasks are considered simultaneously, with the hope that by an appropriate sharing of information across tasks, each task may benefit from th...
This article proposes a research agenda aimed at enabling optimized testing and analysis processes and tools to support component-based software development communities. We hypoth...
Individual, unaided human abilities are constrained. Media have helped us to transcend boundaries in thinking, working, learning, and collaborating by supporting distributed intel...