In this paper the sequential prediction problem with expert advice is considered for the case where losses of experts suffered at each step cannot be bounded in advance. We presen...
The aim of transfer learning is to accelerate learning in related domains. In reinforcement learning, many different features such as a value function and a policy can be transfer...
Design becomes more and more the art of bringing together expertise and experts from different domains in creating future products. Synthetical knowledge and hands-on skills in des...
Jun Hu, Wei Chen, Christoph Bartneck, Matthias Rau...
The goal of transfer learning is to improve the learning of a new target concept given knowledge of related source concept(s). We introduce the first boosting-based algorithms for...
Abstract. We consider the design of online master algorithms for combining the predictions from a set of experts where the absolute loss of the master is to be close to the absolut...
Jacob Abernethy, John Langford, Manfred K. Warmuth