2 search results - page 1 / 1 » Sparse Algorithms Are Not Stable: A No-Free-Lunch Theorem |
PAMI
2012
11 years 7 months ago
2012
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...
TSP
2008
13 years 4 months ago
2008
One of the fundamental assumptions in traditional sampling theorems is that the signals to be sampled come from a single vector space (e.g. bandlimited functions). However, in many...