results for au:Negrinho_R in:cs
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 through a slow trial and error process guided mainly by intuition. In this paper we describe a framework for automatically designing and training deep models. We propose an extensible and modular language that allows the human expert to compactly represent complex search spaces over architectures and their hyperparameters. The resulting search spaces are tree-structured and therefore easy to traverse. Models can be automatically compiled to computational graphs once values for all hyperparameters have been chosen. We can leverage the structure of the search space to introduce different model search algorithms, such as random search, Monte Carlo tree search (MCTS), and sequential model-based optimization (SMBO). We present experiments comparing the different algorithms on CIFAR-10 and show that MCTS and SMBO outperform random search. In addition, these experiments show that our framework can be used effectively for model discovery, as it is possible to describe expressive search spaces and discover competitive models without much effort from the human expert. Code for our framework and experiments has been made publicly available.
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 model, and use the empirical Bayes method to transform the underlying inference problem into a multi-convex optimization problem. We propose a coordinate-wise minimization algorithm that has a closed form solution for each block subproblem. Naively these solutions would be expensive to compute, but by using the theory of doubly stochastic matrices, we are able to reduce the underlying matrix optimization subproblem into a minimum weight perfect matching problem on a complete bipartite graph, and solve it analytically and efficiently. To solve the weight learning subproblem, we propose three different strategies, including a gradient descent method with linear convergence guarantee when the instances are not shared by multiple tasks, and a numerical solution based on Sylvester equation when instances are shared. We demonstrate the efficiency of our method on both synthetic datasets and real-world datasets. Experiments show that the proposed optimization method is orders of magnitude faster than an off-the-shelf projected gradient method, and our model is able to exploit the correlation structures among multiple tasks and features.