Multiclass learning with simplex coding
Author(s)Mroueh, Youssef; Poggio, Tomaso A.; Rosasco, Lorenzo Andrea; Slotine, Jean-Jacques E.
MetadataShow full item record
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.
DepartmentMassachusetts Institute of Technology. Center for Biological & Computational Learning; Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences; Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science; Massachusetts Institute of Technology. Department of Mechanical Engineering; McGovern Institute for Brain Research at MIT
Advances in Neural Information Processing Systems (NIPS)
Neural Information Processing Systems Foundation
Mroueh, Youssef, Tomaso Poggio, Lorenzo Rosasco, and Jean-Jacques E. Slotine. "Multiclass learning with simplex coding." Advances in Neural Information Processing Systems 25 (2012).
Author's final manuscript