We define and solve a simple extension of the ski-rental problem [4]. In the classical version, the algorithm needs to decide when to switch from renting to buying. In our version...
We present a new online learning algorithm in the selective sampling framework, where labels must be actively queried before they are revealed. We prove bounds on the regret of ou...
We consider a network providing Differentiated Services (DiffServ) which allow network service providers to offer different levels of Quality of Service (QoS) to different traffic...
We propose a model-based learning algorithm, the Adaptive Aggregation Algorithm (AAA), that aims to solve the online, continuous state space reinforcement learning problem in a de...
Online prediction methods are typically presented as serial algorithms running on a single processor. However, in the age of web-scale prediction problems, it is increasingly comm...
Ofer Dekel, Ran Gilad-Bachrach, Ohad Shamir, Lin X...