Sciweavers

2168 search results - page 9 / 434
» Randomized Algorithms and Complexity Theory
Sort
View
COMPGEOM
2009
ACM
15 years 6 months ago
Randomly removing g handles at once
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...
CORR
2010
Springer
101views Education» more  CORR 2010»
14 years 11 months ago
Online Learning: Random Averages, Combinatorial Parameters, and Learnability
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
ICML
1999
IEEE
16 years 10 days ago
Machine-Learning Applications of Algorithmic Randomness
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...
Volodya Vovk, Alexander Gammerman, Craig Saunders
GECCO
2007
Springer
193views Optimization» more  GECCO 2007»
15 years 5 months ago
Approximating covering problems by randomized search heuristics using multi-objective models
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,...