267 search results - page 38 / 54 » Convex optimization for the design of learning machines |
SDM
2011
SIAM
12 years 10 months ago
2011
SIAM
In many real world prediction problems the output is a structured object like a sequence or a tree or a graph. Such problems range from natural language processing to computationa...
CDC
2008
IEEE
13 years 8 months ago
2008
IEEE
Minimizing the rank of a matrix subject to constraints is a challenging problem that arises in many applications in control theory, machine learning, and discrete geometry. This c...
CORR
2010
Springer
13 years 6 months ago
2010
Springer
Structured output prediction is an important machine learning problem both in theory and practice, and the max-margin Markov network (M3 N) is an effective approach. All state-of-...
ICANNGA
2009
Springer
14 years 2 months ago
2009
Springer
Many complex, real world phenomena are difficult to study directly using controlled experiments. Instead, the use of computer simulations has become commonplace as a feasible alte...
NIPS
2007
13 years 9 months ago
2007
This paper1 explores the use of a Maximal Average Margin (MAM) optimality principle for the design of learning algorithms. It is shown that the application of this risk minimizati...