Sciweavers

Share
ICML
2005
IEEE
10 years 20 days ago
Hierarchic Bayesian models for kernel learning
The integration of diverse forms of informative data by learning an optimal combination of base kernels in classification or regression problems can provide enhanced performance w...
Mark Girolami, Simon Rogers
ICML
2005
IEEE
10 years 20 days ago
Closed-form dual perturb and combine for tree-based models
This paper studies the aggregation of predictions made by tree-based models for several perturbed versions of the attribute vector of a test case. A closed-form approximation of t...
Pierre Geurts, Louis Wehenkel
ICML
2005
IEEE
10 years 20 days ago
Optimal assignment kernels for attributed molecular graphs
We propose a new kernel function for attributed molecular graphs, which is based on the idea of computing an optimal assignment from the atoms of one molecule to those of another ...
Andreas Zell, Florian Sieker, Holger Fröhlich...
ICML
2005
IEEE
10 years 20 days ago
Supervised clustering with support vector machines
Supervised clustering is the problem of training a clustering algorithm to produce desirable clusterings: given sets of items and complete clusterings over these sets, we learn ho...
Thomas Finley, Thorsten Joachims
ICML
2005
IEEE
10 years 20 days ago
Experimental comparison between bagging and Monte Carlo ensemble classification
Properties of ensemble classification can be studied using the framework of Monte Carlo stochastic algorithms. Within this framework it is also possible to define a new ensemble c...
Roberto Esposito, Lorenza Saitta
ICML
2005
IEEE
10 years 20 days ago
Reinforcement learning with Gaussian processes
Gaussian Process Temporal Difference (GPTD) learning offers a Bayesian solution to the policy evaluation problem of reinforcement learning. In this paper we extend the GPTD framew...
Yaakov Engel, Shie Mannor, Ron Meir
ICML
2005
IEEE
10 years 20 days ago
Combining model-based and instance-based learning for first order regression
T ORDER REGRESSION (EXTENDED ABSTRACT) Kurt Driessensa Saso Dzeroskib a Department of Computer Science, University of Waikato, Hamilton, New Zealand (kurtd@waikato.ac.nz) b Departm...
Kurt Driessens, Saso Dzeroski
ICML
2005
IEEE
10 years 20 days ago
A practical generalization of Fourier-based learning
This paper presents a search algorithm for finding functions that are highly correlated with an arbitrary set of data. The functions found by the search can be used to approximate...
Adam Drake, Dan Ventura
ICML
2005
IEEE
10 years 20 days ago
Learning as search optimization: approximate large margin methods for structured prediction
Mappings to structured output spaces (strings, trees, partitions, etc.) are typically learned using extensions of classification algorithms to simple graphical structures (eg., li...
Daniel Marcu, Hal Daumé III
ICML
2005
IEEE
10 years 20 days ago
Hedged learning: regret-minimization with learning experts
In non-cooperative multi-agent situations, there cannot exist a globally optimal, yet opponent-independent learning algorithm. Regret-minimization over a set of strategies optimiz...
Yu-Han Chang, Leslie Pack Kaelbling
books