It was shown in [11] that any orientable graph of genus g can be probabilistically embedded into a graph of genus g − 1 with constant distortion. Removing handles one by one giv...
Glencora Borradaile, James R. Lee, Anastasios Sidi...
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
Most machine learning algorithms share the following drawback: they only output bare predictions but not the con dence in those predictions. In the 1960s algorithmic information t...
The main aim of randomized search heuristics is to produce good approximations of optimal solutions within a small amount of time. In contrast to numerous experimental results, th...
Tobias Friedrich, Nils Hebbinghaus, Frank Neumann,...