Sciweavers

8381 search results - page 1191 / 1677
» The security of machine learning
Sort
View
COLT
2008
Springer
15 years 8 months ago
Injective Hilbert Space Embeddings of Probability Measures
A Hilbert space embedding for probability measures has recently been proposed, with applications including dimensionality reduction, homogeneity testing and independence testing. ...
Bharath K. Sriperumbudur, Arthur Gretton, Kenji Fu...
COLT
2008
Springer
15 years 8 months ago
Relating Clustering Stability to Properties of Cluster Boundaries
In this paper, we investigate stability-based methods for cluster model selection, in particular to select the number K of clusters. The scenario under consideration is that clust...
Shai Ben-David, Ulrike von Luxburg
COLT
2008
Springer
15 years 8 months ago
On the Equivalence of Weak Learnability and Linear Separability: New Relaxations and Efficient Boosting Algorithms
Boosting algorithms build highly accurate prediction mechanisms from a collection of lowaccuracy predictors. To do so, they employ the notion of weak-learnability. The starting po...
Shai Shalev-Shwartz, Yoram Singer
COLT
2008
Springer
15 years 8 months ago
Model Selection and Stability in k-means Clustering
Clustering Stability methods are a family of widely used model selection techniques applied in data clustering. Their unifying theme is that an appropriate model should result in ...
Ohad Shamir, Naftali Tishby
COLT
2008
Springer
15 years 8 months ago
When Random Play is Optimal Against an Adversary
We analyze a sequential game between a Gambler and a Casino. The Gambler allocates bets from a limited budget over a fixed menu of gambling events that are offered at equal time i...
Jacob Abernethy, Manfred K. Warmuth, Joel Yellin
« Prev « First page 1191 / 1677 Last » Next »