Recent approaches to learning structured predictors often require approximate inference for tractability; yet its effects on the learned model are unclear. Meanwhile, most learnin...
The power of sparse signal coding with learned overcomplete dictionaries has been demonstrated in a variety of applications and fields, from signal processing to statistical infe...
Chord progressions are the building blocks from which tonal music is constructed. Inferring chord progressions is thus an essential step towards modeling long term dependencies in...
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...
We propose a calculus of local equations over one-way measurement patterns [1], which preserves interpretations, and allows the rewriting of any pattern to a standard form where e...