Renato Negrinho

Learn More
We propose a general framework for regularization based on group-induced majorization. In this framework, a group is defined to act on the parameter space and an orbit is fixed; to control complexity, the model parameters are confined to the convex hull of this orbit (the orbitope). We recover several well-known regularizers as particular cases, and reveal(More)
In deep learning, performance is strongly affected by the choice of architecture and hyperparameters. While there has been extensive work on automatic hyperparameter optimization for simple spaces, complex spaces such as the space of deep architectures remain largely unexplored. As a result, the choice of architecture is done manually by the human expert(More)
In this paper we propose a multi-convex framework for multi-task learning that improves predictions by learning relationships both between tasks and between features. Our framework is a generalization of related methods in multi-task learning, that either learn task relationships, or feature relationships, but not both. We start with a hierarchical Bayesian(More)
  • 1