While Deep Neural Networks (DNNs) have achieved tremendous success for large vocabulary continuous speech recognition (LVCSR) tasks, training of these networks is slow. One reason is that DNNs are trained with a large number of training parameters (i.e., 10-50 million). Because networks are trained with a large number of output targets to achieve good performance, the majority of these parameters are in the final weight layer. In this paper, we propose a low-rank matrix factorization of the final weight layer. We apply this low-rank technique to DNNs for both acoustic modeling and language modeling. We show on three different LVCSR tasks ranging between 50-400 hrs, that a low-rank factorization reduces the number of parameters of the network by 30-50%. This results in roughly an equivalent reduction in training time, without a significant loss in final recognition accuracy, compared to a full-rank representation.

No abstract

Large scale learning is often realistic only in a semi-supervised setting where a small set of labeled examples is available together with a large collection of unlabeled data. In many information retrieval and data mining applications, linear classifiers are strongly preferred because of their ease of implementation, interpretability and empirical performance. In this work, we present a family of semi-supervised linear support vector classifiers that are designed to handle partially-labeled sparse datasets with possibly very large number of examples and features. At their core, our algorithms employ recently developed modified finite Newton techniques. Our contributions in this paper are as follows: (a) We provide an implementation of Transductive SVM (TSVM) that is significantly more efficient and scalable than currently used dual techniques, for linear classification problems involving large, sparse datasets. (b) We propose a variant of TSVM that involves multiple switching of labels. Experimental results show that this variant provides an order of magnitude further improvement in training efficiency. (c) We present a new algorithm for semi-supervised learning based on a Deterministic Annealing (DA) approach. This algorithm alleviates the problem of local minimum in the TSVM optimization procedure while also being computationally attractive. We conduct an empirical study on several document classification tasks which confirms the value of our methods in large scale semisupervised settings.

Inspired by co-training, many multi-view semi-supervised kernel methods implement the following idea: find a function in each of multiple Reproducing Kernel Hilbert Spaces (RKHSs) such that (a) the chosen functions make similar predictions on unlabeled examples, and (b) the average prediction given by the chosen functions performs well on labeled examples. In this paper, we construct a single RKHS with a data-dependent "co-regularization" norm that reduces these approaches to standard supervised learning. The reproducing kernel for this RKHS can be explicitly derived and plugged into any kernel method, greatly extending the theoretical and algorithmic scope of coregularization. In particular, with this development, the Rademacher complexity bound for co-regularization given in (Rosenberg & Bartlett, 2007) follows easily from wellknown results. Furthermore, more refined bounds given by localized Rademacher complexity can also be easily applied. We propose a co-regularization based algorithmic alternative to manifold regularization (Belkin et al., 2006;Sindhwani et al., 2005a) that leads to major empirical improvements on semi-supervised tasks. Unlike the recently proposed transductive approach of (Yu et al., 2008), our RKHS formulation is truly semisupervised and naturally extends to unseen test data.

No abstract