The most basic assumption used in statistical learning theory is that training data and test data are drawn from the same underlying distribution. Unfortunately, in many applications, the “in-domain” test data is drawn from a distribution that is related, but not identical, to the “out-of-domain” distribution of the training data. We consider the common case in which labeled out-of-domain data ...

Domain adaptation algorithms address a key issue in applied machine learning: How can we train a system under a source distribution but achieve high performance under a different target distribution? We tackle this question for divergent distributions where crucial predictive target features may not even have support under the source distribution. In this setting, the key intuition is that that...

Top-performing deep architectures are trained on massive amounts of labeled data. In the absence of labeled data for a certain task, domain adaptation often provides an attractive option given that labeled data of similar nature but from a different domain (e.g. synthetic images) are available. Here, we propose a new approach to domain adaptation in deep architectures that can be trained on lar...

This work provides a framework for addressing the problem of supervised domain adaptation with deep models. The main idea is to exploit adversarial learning to learn an embedded subspace that simultaneously maximizes the confusion between two domains while semantically aligning their embedding. The supervised setting becomes attractive especially when there are only a few target data samples th...

The machine learning approach to problems from computational biology is to learn models from labeled training examples. A common problem in supervised learning is the lack of sufficient training data. Often, however, there exists a large body of data on a different, but related problem. In order to boost performance on our problem of interest, we would like to utilize information from this rela...

Current state-of-the-art approaches in domain adaptation and fusion show promising results with either labeled or unlabeled task-relevant target-domain training data. However, the fact that the task-relevant target-domain training data can be unavailable is often ignored by the prior works. To tackle this issue, instead of using the task-relevant target-domain training data, we propose zeroshot...

The unsupervised image-to-image translation aims at finding a mapping between the source (A) and target (B) image domains, where in many applications aligned image pairs are not available at training. This is an ill-posed learning problem since it requires inferring the joint probability distribution from marginals. Joint learning of coupled mappings FAB : A → B and FBA : B → A is commonly used...

Empirical risk minimization offers well-known learning guarantees when training and test data come from the same domain. In the real world, though, we often wish to adapt a classifier from a source domain with a large amount of training data to different target domain with very little training data. In this work we give uniform convergence bounds for algorithms that minimize a convex combinatio...