Sciweavers

1301 search results - page 43 / 261
» Bounded Version Vectors
Sort
View
AAAI
1997
15 years 5 months ago
Worst-Case Absolute Loss Bounds for Linear Learning Algorithms
The absolute loss is the absolute difference between the desired and predicted outcome. I demonstrateworst-case upper bounds on the absolute loss for the perceptron algorithm and ...
Tom Bylander
133
Voted
MFCS
1997
Springer
15 years 8 months ago
Resolution Proofs, Exponential Bounds, and Kolmogorov Complexity
We prove an exponential lower bound for the length of any resolution proof for the same set of clauses as the one used by Urquhart [13]. Our contribution is a significant simpli...
Uwe Schöning
ANOR
2008
171views more  ANOR 2008»
15 years 4 months ago
A branch and bound method for the job-shop problem with sequence-dependent setup times
This paper deals with the job-shop scheduling problem with sequencedependent setup times. We propose a new method to solve the makespan minimization problem to optimality. The met...
Christian Artigues, Dominique Feillet
ML
2008
ACM
162views Machine Learning» more  ML 2008»
15 years 3 months ago
Incorporating prior knowledge in support vector regression
This paper explores the addition of constraints to the linear programming formulation of the support vector regression problem for the incorporation of prior knowledge. Equality an...
Fabien Lauer, Gérard Bloch
138
Voted
COLT
2001
Springer
15 years 8 months ago
Rademacher and Gaussian Complexities: Risk Bounds and Structural Results
We investigate the use of certain data-dependent estimates of the complexity of a function class, called Rademacher and Gaussian complexities. In a decision theoretic setting, we ...
Peter L. Bartlett, Shahar Mendelson