We develop improved risk bounds for function estimation with models such as single hidden layer neural nets, using a penalized least squares criterion to select the size of the mod...
We present an improvement of Noviko 's perceptron convergence theorem. Reinterpreting this mistakebound as a margindependent sparsity guarantee allows us to give a PAC{style ...
Thore Graepel, Ralf Herbrich, Robert C. Williamson
This paper presents a new analysis and design method for model reference adaptive control(MRAC) with arbitrary bounded input nonlinearities. The adaptive algorithm ensures that th...
The estimation of a sparse vector in the linear model is a fundamental problem in signal processing, statistics, and compressive sensing. This paper establishes a lower bound on t...
Let G be a graph with n vertices and independence number . Hadwiger's conjecture implies that G contains a clique minor of order at least n/. In 1982, Duchet and Meyniel prov...