Cross-domain data reconstruction methods derive a shared transformation across source and target domains. These methods usually make a specific assumption on noise, which exhibits limited ability when the target data are contaminated by different kinds of complex noise in practice. To enhance the robustness of domain adaptation under severe noise conditions, this paper proposes a novel reconstruction based algorithm in an information-theoretic setting. Specifically, benefiting from the theoretical property of correntropy, the proposed algorithm is distinguished with: detecting the contaminated target samples without making any specific assumption on noise; greatly suppressing the negative influence of noise on cross-domain transformation. Moreover, a relative entropy based regularization of the transformation is incorporated to avoid trivial solutions with the reaped theoretic advantages, i.e., non-negativity and scale-invariance. For optimization, a half-quadratic technique is developed to minimize the non-convex information-theoretic objectives with explicitly guaranteed convergence. Experiments on two real-world domain adaptation tasks demonstrate the superiority of our method.

Domain adaptation aims at generalizing a high-performance learner on a target domain via utilizing the knowledge distilled from a source domain which has a different but related data distribution. One solution to domain adaptation is to learn domain invariant feature representations while the learned representations should also be discriminative in prediction. To learn such representations, domain adaptation frameworks usually include a domain invariant representation learning approach to measure and reduce the domain discrepancy, as well as a discriminator for classification. Inspired by Wasserstein GAN, in this paper we propose a novel approach to learn domain invariant feature representations, namely Wasserstein Distance Guided Representation Learning (WDGRL). WDGRL utilizes a neural network, denoted by the domain critic, to estimate empirical Wasserstein distance between the source and target samples and optimizes the feature extractor network to minimize the estimated Wasserstein distance in an adversarial manner. The theoretical advantages of Wasserstein distance for domain adaptation lie in its gradient property and promising generalization bound. Empirical studies on common sentiment and image classification adaptation datasets demonstrate that our proposed WDGRL outperforms the state-of-the-art domain invariant representation learning approaches.

The determinantal point process (DPP) has been receiving increasing attention in machine learning as a generative model of subsets consisting of relevant and diverse items. Recently, there has been a significant progress in developing efficient algorithms for learning the kernel matrix that characterizes a DPP. Here, we propose a dynamic DPP, which is a DPP whose kernel can change over time, and develop efficient learning algorithms for the dynamic DPP. In the dynamic DPP, the kernel depends on the subsets selected in the past, but we assume a particular structure in the dependency to allow efficient learning. We also assume that the kernel has a low rank and exploit a recently proposed learning algorithm for the DPP with low-rank factorization, but also show that its bottleneck computation can be reduced from O ( M 2 K ) time to O ( M K 2 ) time, where M is the number of items under consideration, and K is the rank of the kernel, which can be set smaller than M by orders of magnitude.

Learning an optimal policy from a multi-modal reward function is a challenging problem in reinforcement learning (RL). Hierarchical RL (HRL) tackles this problem by learning a hierarchicalpolicy, where multiple option policies are in charge of different strategies corresponding to modes of a reward function and a gating policy selects the best option for a given context. Although HRL has been demonstrated to be promising, current state-of-the-art methods cannot still perform well in complex real-world problems due to the difficulty of identifying modes of the reward function. In this paper, we propose a novel method called hierarchical policy search via return-weighted density estimation (HPSDE), which can efficiently identify the modes through density estimation with return-weighted importance sampling. Our proposed method finds option policies corresponding to the modes of the return function and automatically determines the number and the location of option policies, which significantly reduces the burden of hyper-parameters tuning. Through experiments, we demonstrate that the proposed HPSDE successfully learns option policies corresponding to modes of the return function and that it can be successfully applied to a motion planning problem of a redundant robotic manipulator.

The random features method is an efficient method to approximate the kernel function. In this paper, we propose novel random features called "alternating circulant random features,'' which consist of a random mixture of independent random structured matrices. Existing fast random features exploit random sign flipping to reduce the correlation between features. Sign flipping works well on random Fourier features for real-valued shift-invariant kernels because the corresponding weight distribution is symmetric. However, this method cannot be applied to random Laplace features directly because the distribution is not symmetric. The method proposed herein yields alternating circulant random features, with the correlation between features being reduced through the random sampling of weights from multiple independent random structured matrices instead of via random sign flipping. The proposed method facilitates rapid calculation by employing structured matrices. In addition, the weight distribution is preserved because sign flipping is not implemented. The performance of the proposed alternating circulant random features method is theoretically and empirically evaluated.

Embedding-based methods for knowledge base completion (KBC) learn representations of entities and relations in a vector space, along with the scoring function to estimate the likelihood of relations between entities. The learnable class of scoring functions is designed to be expressive enough to cover a variety of real-world relations, but this expressive comes at the cost of an increased number of parameters. In particular, parameters in these methods are superfluous for relations that are either symmetric or antisymmetric. To mitigate this problem, we propose a new L1 regularizer for Complex Embeddings, which is one of the state-of-the-art embedding-based methods for KBC. This regularizer promotes symmetry or antisymmetry of the scoring function on a relation-by-relation basis, in accordance with the observed data. Our empirical evaluation shows that the proposed method outperforms the original Complex Embeddings and other baseline methods on the FB15k dataset.

In classification, an algorithm learns to classify a given instance based on a set of observed attribute values. In many real world cases testing the value of an attribute incurs a cost. Furthermore, there can also be a cost associated with the misclassification of an instance. Cost sensitive classification attempts to minimize the expected cost of classification, by deciding after each observed attribute value, which attribute to measure next. In this paper we suggest Markov Decision Processes as a modeling tool for cost sensitive classification. We construct standard decision trees over all attribute subsets, and the leaves of these trees become the state space of our MDP. At each phase we decide on the next attribute to measure, balancing the cost of the measurement and the classification accuracy. We compare our approach to a set of previous approaches, showing our approach to work better for a range of misclassification costs.

Feature selection is effective in preparing high-dimensional data for a variety of learning tasks such as classification, clustering and anomaly detection. A vast majority of existing feature selection methods assume that all instances share some common patterns manifested in a subset of shared features. However, this assumption is not necessarily true in many domains where data instances could show high individuality. For example, in the medical domain, we need to capture the heterogeneous nature of patients for personalized predictive modeling, which could be characterized by a subset of instance-specific features. Motivated by this, we propose to study a novel problem of personalized feature selection. In particular, we investigate the problem in an unsupervised scenario as label information is usually hard to obtain in practice. To be specific, we present a novel unsupervised personalized feature selection framework UPFS to find some shared features by all instances and instance-specific features tailored to each instance. We formulate the problem into a principled optimization framework and provide an effective algorithm to solve it. Experimental results on real-world datasets verify the effectiveness of the proposed UPFS framework.

Dialogue Act recognition associate dialogue acts (i.e., semantic labels) to utterances in a conversation. The problem of associating semantic labels to utterances can be treated as a sequence labeling problem. In this work, we build a hierarchical recurrent neural network using bidirectional LSTM as a base unit and the conditional random field (CRF) as the top layer to classify each utterance into its corresponding dialogue act. The hierarchical network learns representations at multiple levels, i.e., word level, utterance level, and conversation level. The conversation level representations are input to the CRF layer, which takes into account not only all previous utterances but also their dialogue acts, thus modeling the dependency among both, labels and utterances, an important consideration of natural dialogue. We validate our approach on two different benchmark data sets, Switchboard and Meeting Recorder Dialogue Act, and show performance improvement over the state-of-the-art methods by 2.2% and 4.1% absolute points, respectively. It is worth noting that the inter-annotator agreement on Switchboard data set is 84%, and our method is able to achieve the accuracy of about 79% despite being trained on the noisy data.

Binary embedding refers to methods for embedding points in R d into vertices of a Hamming cube of dimension k, such that the normalized Hamming distance well preserves the pre-defined similarity between vectors in the original space. A common approach to binary embedding is to use random projection with unstructured projection, followed by one-bit quantization to produce binary codes, which has been proven that k = O (ε -2 log n ) is required to approximate the angle up to epsilon-distortion, where n is the number of data. Of particular interest in this paper is circulant binary embedding (CBE) with angle preservation, where a random circulant matrix is used for projection. It yields comparable performance while achieving the nearly linear time and space complexities, compared to embedding methods relying on unstructured projection. To support promising empirical results, several non-asymptotic analysis have been introduced to establish conditions on the number of bits to meet epsilon-distortion embedding, where one of state-of-the-art achieves the optimal sample complexity k = O (ε -3 log n ) while the distortion rate ε -3 is far from the optimality, compared to k = O (ε -2 log n ). In this paper, to support promising empirical results of CBE, we extend the previous theoretical framework to address the optimal condition on the number of bits, achieving that CBE with k = O(ε -2 log n) approximates the angle up to ε-distortion under mild assumptions. We also provide numerical experiments to support our theoretical results.