We consider learning in a Markov decision process where we are not explicitly given a reward function, but where instead we can observe an expert demonstrating the task that we wa...
Abstract. Type Extension Trees (TET) have been recently introduced as an expressive representation language allowing to encode complex combinatorial features of relational entities...
Marco Lippi, Manfred Jaeger, Paolo Frasconi, Andre...
We develop a theory of online learning by defining several complexity measures. Among them are analogues of Rademacher complexity, covering numbers and fatshattering dimension fro...
Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari
This is an introductory book about machine learning. Notice that this is a draft book. It may contain typos, mistakes, etc.
The book covers the following topics: Boolean Functio...
We examine the structure of families of distortion balls from the perspective of Kolmogorov complexity. Special attention is paid to the canonical rate-distortion function of a so...