Abstract. A well-known result by Stein shows that regularized estimators with small bias often yield better estimates than unbiased estimators. In this paper, we adapt this spirit ...
The notion of algorithmic stability has been used effectively in the past to derive tight generalization bounds. A key advantage of these bounds is that they are designed for spec...
We discuss the modelling of FAST TCP and prove four stability results. Using the traditional continuous-time flow model, we prove, for general networks, that FAST TCP is globally ...
Abstract—We consider two desired properties of learning algorithms: sparsity and algorithmic stability. Both properties are believed to lead to good generalization ability. We sh...
We give a new exposition and proof of a generalized CSS construction for nonbinary quantum error-correcting codes. Using this we construct nonbinary quantum stabilizer codes with ...