We showed that the notion of output regularization and Fenchel duality provide simple core principles, unifying many existing loss functions, and allowing to create useful new ones easily, on a large spectrum of tasks. We characterized a tight con...
Factorization machines and polynomial networks are supervised polynomial models based on an efficient low-rank decomposition. We extend these models to the multi-output setting, i.e., for learning vector-valued functions, with application to multi...
Credentials & highlights
- Project Views