Inductive algorithms rely strongly on their representational biases, Constructive induction can mitigate representational inadequacies. This paper introduces the notion of a relat...
—In this paper, we present a near ML-achieving sphere search technique that reduces the number of search operations significantly over existing sphere decoding (SD) algorithms. ...
We propose low-rank representation (LRR) to segment data drawn from a union of multiple linear (or affine) subspaces. Given a set of data vectors, LRR seeks the lowestrank represe...
Dynamic Datastructure Excavation (DDE) is a new approach to extract datastructures from C binaries without any need for debugging symbols. Unlike most existing tools, DDE uses dyn...
In this paper, we examine the problem of learning from noisecontaminated data in high-dimensional space. A new learning approach based on projections onto multi-dimensional ellips...