|
|
|
|
LEADER |
01945 am a22002893u 4500 |
001 |
92319 |
042 |
|
|
|a dc
|
100 |
1 |
0 |
|a Mroueh, Youssef
|e author
|
100 |
1 |
0 |
|a Massachusetts Institute of Technology. Center for Biological & Computational Learning
|e contributor
|
100 |
1 |
0 |
|a Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
|e contributor
|
100 |
1 |
0 |
|a Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
|e contributor
|
100 |
1 |
0 |
|a Massachusetts Institute of Technology. Department of Mechanical Engineering
|e contributor
|
100 |
1 |
0 |
|a McGovern Institute for Brain Research at MIT
|e contributor
|
100 |
1 |
0 |
|a Mroueh, Youssef
|e contributor
|
100 |
1 |
0 |
|a Poggio, Tomaso A.
|e contributor
|
100 |
1 |
0 |
|a Rosasco, Lorenzo Andrea
|e contributor
|
100 |
1 |
0 |
|a Slotine, Jean-Jacques E.
|e contributor
|
700 |
1 |
0 |
|a Poggio, Tomaso A.
|e author
|
700 |
1 |
0 |
|a Rosasco, Lorenzo Andrea
|e author
|
700 |
1 |
0 |
|a Slotine, Jean-Jacques E.
|e author
|
245 |
0 |
0 |
|a Multiclass learning with simplex coding
|
260 |
|
|
|b Neural Information Processing Systems Foundation,
|c 2014-12-16T15:43:57Z.
|
856 |
|
|
|z Get fulltext
|u http://hdl.handle.net/1721.1/92319
|
520 |
|
|
|a In this paper we discuss a novel framework for multiclass learning, defined by a suitable coding/decoding strategy, namely the simplex coding, that allows us to generalize to multiple classes a relaxation approach commonly used in binary classification. In this framework, we develop a relaxation error analysis that avoids constraints on the considered hypotheses class. Moreover, using this setting we derive the first provably consistent regularized method with training/tuning complexity that is independent to the number of classes. We introduce tools from convex analysis that can be used beyond the scope of this paper.
|
546 |
|
|
|a en_US
|
655 |
7 |
|
|a Article
|
773 |
|
|
|t Advances in Neural Information Processing Systems (NIPS)
|