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 ...
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...
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...
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...
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 ...