Sciweavers

Share
ICML
2007
IEEE
10 years 4 months ago
Constructing basis functions from directed graphs for value function approximation
Basis functions derived from an undirected graph connecting nearby samples from a Markov decision process (MDP) have proven useful for approximating value functions. The success o...
Jeffrey Johns, Sridhar Mahadevan
ICML
2007
IEEE
10 years 4 months ago
Experimental perspectives on learning from imbalanced data
We present a comprehensive suite of experimentation on the subject of learning from imbalanced data. When classes are imbalanced, many learning algorithms can suffer from the pers...
Jason Van Hulse, Taghi M. Khoshgoftaar, Amri Napol...
ICML
2007
IEEE
10 years 4 months ago
Sparse probabilistic classifiers
The scores returned by support vector machines are often used as a confidence measures in the classification of new examples. However, there is no theoretical argument sustaining ...
Romain Hérault, Yves Grandvalet
ICML
2007
IEEE
10 years 4 months ago
Efficient inference with cardinality-based clique potentials
Many collective labeling tasks require inference on graphical models where the clique potentials depend only on the number of nodes that get a particular label. We design efficien...
Rahul Gupta, Ajit A. Diwan, Sunita Sarawagi
ICML
2007
IEEE
10 years 4 months ago
Recovering temporally rewiring networks: a model-based approach
A plausible representation of relational information among entities in dynamic systems such as a living cell or a social community is a stochastic network which is topologically r...
Fan Guo, Steve Hanneke, Wenjie Fu, Eric P. Xing
ICML
2007
IEEE
10 years 4 months ago
Best of both: a hybridized centroid-medoid clustering heuristic
Although each iteration of the popular kMeans clustering heuristic scales well to larger problem sizes, it often requires an unacceptably-high number of iterations to converge to ...
Nizar Grira, Michael E. Houle
ICML
2007
IEEE
10 years 4 months ago
Bayesian actor-critic algorithms
We1 present a new actor-critic learning model in which a Bayesian class of non-parametric critics, using Gaussian process temporal difference learning is used. Such critics model ...
Mohammad Ghavamzadeh, Yaakov Engel
ICML
2007
IEEE
10 years 4 months ago
Combining online and offline knowledge in UCT
The UCT algorithm learns a value function online using sample-based search. The TD() algorithm can learn a value function offline for the on-policy distribution. We consider three...
Sylvain Gelly, David Silver
ICML
2007
IEEE
10 years 4 months ago
Manifold-adaptive dimension estimation
Intuitively, learning should be easier when the data points lie on a low-dimensional submanifold of the input space. Recently there has been a growing interest in algorithms that ...
Amir Massoud Farahmand, Csaba Szepesvári, J...
ICML
2007
IEEE
10 years 4 months ago
Non-isometric manifold learning: analysis and an algorithm
In this work we take a novel view of nonlinear manifold learning. Usually, manifold learning is formulated in terms of finding an embedding or `unrolling' of a manifold into ...
Piotr Dollár, Serge J. Belongie, Vincent Ra...
books