Online learning represents a family of machine learning methods, where a learner attempts
to tackle some predictive (or any type of decision-making) task by learning from a sequence …

Linear classification is a useful tool in machine learning and data mining. For some data in a
rich dimensional space, the performance (ie, testing accuracy) of linear classifiers has …

This paper presents the results of the WMT17 shared tasks, which included three machine
translation (MT) tasks (news, biomedical, and multimodal), two evaluation tasks (metrics and …

Recent studies have highlighted the vulnerability of deep neural networks (DNNs) to
adversarial examples—a visually indistinguishable adversarial image can easily be crafted …

Structured pruning is a commonly used technique in deploying deep neural networks
(DNNs) onto resource-constrained devices. However, the existing pruning methods are …

In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially
outperforms training from scratch. When using fine-tuning, the underlying assumption is that …

We consider a family of algorithms that successively sample and minimize simple stochastic
models of the objective function. We show that under reasonable conditions on …

To attain a favorable performance on large-scale datasets, convolutional neural networks
(CNNs) are usually designed to have very high capacity involving millions of parameters. In …

We consider the problem of minimizing the sum of two convex functions: one is the average
of a large number of smooth component functions, and the other is a general convex …

We present a new family of subgradient methods that dynamically incorporate knowledge of
the geometry of the data observed in earlier iterations to perform more informative gradient …