Publications
Explore 317 academic publications
Rademacher Processes and Bounding the Risk of Function Learning
We construct data dependent upper bounds on the risk in function learning problems. The bounds are based on local norms of the Rademacher process indexed by the underlying funct...
Computer Simulation of Biomolecular Systems
While the study of biomolecular systems by computer simulation has been contributing to our understanding of the mechanics and energetics of these systems for fifteen years, we ...
An adaptive least squares algorithm for the efficient training of artificial neural networks
A novel learning algorithm is developed for the training of multilayer feedforward neural networks, based on a modification of the Marquardt-Levenberg least-squares optimization...
A Convergence Theorem for Competitive Bidding with Differential Information
IN THIS PAPER we investigate the properties of the winning bid in a sealed bid tender auction where each player has private information. We find that it is possible for the winn...
A new least-squares refinement technique based on the fast Fourier transform algorithm
A new atomic-parameters least-squares refinement method is presented which makes use of the fast Fourier transform algorithm at all stages of the computation. For large structur...
A loop-free extended Bellman-Ford routing protocol without bouncing effect
Distributed algorithms for shortest-path problems are important in the context of routing in computer communication networks. We present a protocol that maintains the shortest-p...
On a Conjecture of Huber Concerning the Convergence of Projection Pursuit Regression
We generalize the projection pursuit procedure of Friedman and Stuetzle (abstract version) and prove strong convergence. This answers a question of Huber.
The reduced linear equation method in coupled cluster theory.
A numerical procedure for efficiently solving large systems of linear equations is presented. The approach, termed the reduced linear equation (RLE) method, is illustrated by so...