Exact structured inference with neural network scoring functions is computationally challenging but several methods have been proposed for approximating inference. One approach is to perform gradient descent with respect to the output structure directly (Belanger and McCallum, 2016). Another approach, proposed recently, is to train a neural network (an "inference network") to perform inference (Tu and Gimpel, 2018). In this paper, we compare these two families of inference methods on three sequence labeling datasets. We choose sequence labeling because it permits us to use exact inference as a benchmark in terms of speed, accuracy, and search error. Across datasets, we demonstrate that inference networks achieve a better speed/accuracy/search error trade-off than gradient descent, while also being faster than exact inference at similar accuracy levels. We find further benefit by combining inference networks and gradient descent, using the former to provide a warm start for the latter.

With the development of information technology, we have witnessed an age of data explosion which produces a large variety of data filled with redundant information. Because dimension reduction is an essential tool which embeds high-dimensional data into a lower-dimensional subspace to avoid redundant information, it has attracted interests from researchers all over the world. However, facing with features from multiple views, it's difficult for most dimension reduction methods to fully comprehended multi-view features and integrate compatible and complementary information from these features to construct low-dimensional subspace directly. Furthermore, most multi-view dimension reduction methods cannot handle features from nonlinear spaces with high dimensions. Therefore, how to construct a multi-view dimension reduction methods which can deal with multi-view features from high-dimensional nonlinear space is of vital importance but challenging. In order to address this problem, we proposed a novel method named Co-regularized Multi-view Sparse Reconstruction Embedding (CMSRE) in this paper. By exploiting correlations of sparse reconstruction from multiple views, CMSRE is able to learn local sparse structures of nonlinear manifolds from multiple views and constructs significative low-dimensional representations for them. Due to the proposed co-regularized scheme, correlations of sparse reconstructions from multiple views are preserved by CMSRE as much as possible. Furthermore, sparse representation produces more meaningful correlations between features from each single view, which helps CMSRE to gain better performances. Various evaluations based on the applications of document classification, face recognition and image retrieval can demonstrate the effectiveness of the proposed approach on multi-view dimension reduction.

Recent years we have witnessed the great popularity of graph representation learning with success in not only node-level tasks such as node classification (Kipf & Welling, 2016a) and link prediction (Zhang & Chen, 2018) but also graph-level tasks such as graph classification (Ying et al., 2018) and graph similarity/distance computation (Bai et al., 2019). There has been a rich body of work (Belkin & Niyogi, 2003; Qiu et al., 2018) on node-level embeddings that turn each node in a graph into a vector preserving node-node proximity (similarity/distance). It is thus natural to raise the question: Can we embed an entire graph into a vector in an unsupervised way, and how? However, most existing methods for graph-level, i.e. whole-graph, embeddings assume a supervised model (Zhang & Chen, 2019), with only a few exceptions such as G KERNELS(Yanardag & Vishwanathan, 2015), which typically count subgraphs for a given graph and can be slow, and GRAPH2VEC(Narayanan et al., 2017), which is transductive. A key challenge facing designing an unsupervised graph-level embedding model is the lack of graphlevel signals in the training stage. Unlike node-level embedding which has a long history in utilizing the link structure of a graph to embed nodes, there lacks such natural proximity (similarity/distance) information between graphs. Supervised methods, therefore, typically resort to graph labels as guidance and use aggregation based methods, e.g. However, this assumption is problematic, as simple aggregation of node embeddings can only preserve limited graph-level properties, which is, however, often insufficient in measuring graphgraph proximity ("inter-graph" information). Inspired by the recent progress on graph proximity modeling (Ktena et al., 2017; Bai et al., 2019), we propose a novel framework, UG RAPHEMBthat employs multi-scale aggregations of node-level embeddings, guided by the graph-graph proximity defined by well-accepted and domain-agnostic graph proximity metrics such as Graph Edit Distance (GED) (Bunke, 1983), Maximum Common Subgraph (MCS) (Bunke & Shearer, 1998), etc. RAPHEMBis to learn high-quality graph-level representations in a completely unsupervised and inductive fashion: During training, it learns a function that maps a graph into a universal embedding space best preserving graph-graph proximity, so that after training, any new graph can be mapped to this embedding space by applying the learned function. Inspired by the recent success of pre-training methods in the text domain, such as ELMO (Peters et al., 2018), B RAPHEMBfirst computes the graph-graph proximity scores, (c) yielding a "hyper-level graph" where each node is a graph in the dataset, and each edge has a proximity score associated with it, representing its weight/strength. RAPHEMBthen trains a function that maps each graph into an embedding which preserves the proximity score.

The problem of combined state and input estimation of linear structural systems based on measured responses and a priori knowledge of structural model is considered. A novel methodology using Gaussian process latent force models is proposed to tackle the problem in a stochastic setting. Gaussian process latent force models (GPLFMs) are hybrid models that combine differential equations representing a physical system with data-driven non-parametric Gaussian process models. In this work, the unknown input forces acting on a structure are modelled as Gaussian processes with some chosen covariance functions which are combined with the mechanistic differential equation representing the structure to construct a GPLFM. The GPLFM is then conveniently formulated as an augmented stochastic state-space model with additional states representing the latent force components, and the joint input and state inference of the resulting model is implemented using Kalman filter. The augmented state-space model of GPLFM is shown as a generalization of the class of input-augmented state-space models, is proven observable, and is robust compared to conventional augmented formulations in terms of numerical stability. The hyperparameters governing the covariance functions are estimated using maximum likelihood optimization based on the observed data, thus overcoming the need for manual tuning of the hyperparameters by trial-and-error. To assess the performance of the proposed GPLFM method, several cases of state and input estimation are demonstrated using numerical simulations on a 10-dof shear building and a 76-storey ASCE benchmark office tower. Results obtained indicate the superior performance of the proposed approach over conventional Kalman filter based approaches.

Recently, a spate of papers have provided positive theoretical results for training over-parameterized neural networks (where the network size is larger than what is needed to achieve low error). The key insight is that with sufficient over-parameterization, gradient-based methods will implicitly leave some components of the network relatively unchanged, so the optimization dynamics will behave as if those components are essentially fixed at their initial random values. In fact, fixing these explicitly leads to the well-known approach of learning with random features. In other words, these techniques imply that we can successfully learn with neural networks, whenever we can successfully learn with random features. In this paper, we first review these techniques, providing a simple and self-contained analysis for one-hidden-layer networks. We then argue that despite the impressive positive results, random feature approaches are also inherently limited in what they can explain. In particular, we rigorously show that random features cannot be used to learn even a single ReLU neuron with standard Gaussian inputs, unless the network size (or magnitude of the weights) is exponentially large. Since a single neuron is learnable with gradient-based methods, we conclude that we are still far from a satisfying general explanation for the empirical success of neural networks.

Future buildings will offer new convenience, comfort, and efficiency possibilities to their residents. Changes will occur to the way people live as technology involves into people's lives and information processing is fully integrated into their daily living activities and objects. The future expectation of smart buildings includes making the residents' experience as easy and comfortable as possible. The massive streaming data generated and captured by smart building appliances and devices contains valuable information that needs to be mined to facilitate timely actions and better decision making. Machine learning and big data analytics will undoubtedly play a critical role to enable the delivery of such smart services. In this paper, we survey the area of smart building with a special focus on the role of techniques from machine learning and big data analytics. This survey also reviews the current trends and challenges faced in the development of smart building services.

Thermal preferences vary from person to person and may change over time. The main objective of this paper is to sequentially pose intelligent queries to occupants in order to optimally learn the indoor air temperature values which maximize their satisfaction. Our central hypothesis is that an occupant's preference relation over indoor air temperature can be described using a scalar function of these temperatures, which we call the "occupant's thermal utility function". Information about an occupant's preference over these temperatures is available to us through their response to thermal preference queries : "prefer warmer," "prefer cooler" and "satisfied" which we interpret as statements about the derivative of their utility function, i.e. the utility function is "increasing", "decreasing" and "constant" respectively. We model this hidden utility function using a Gaussian process prior with built-in unimodality constraint, i.e., the utility function has a unique maximum, and we train this model using Bayesian inference. This permits an expected improvement based selection of next preference query to pose to the occupant, which takes into account both exploration (sampling from areas of high uncertainty) and exploitation (sampling from areas which are likely to offer an improvement over current best observation). We use this framework to sequentially design experiments and illustrate its benefits by showing that it requires drastically fewer observations to learn the maximally preferred temperature values as compared to other methods. This framework is an important step towards the development of intelligent HVAC systems which would be able to respond to occupants' personalized thermal comfort needs. In order to encourage the use of our PE framework and ensure reproducibility in results, we publish an implementation of our work named GPPrefElicit as an open-source package in Python.

Common privacy enhancing technologies fail to effectively hide certain statistical aspects of encrypted traffic, namely individual packets length, packets direction and, packets timing. Recent researches have shown that using such attributes, an adversary is able to extract various information from the encrypted traffic such as the visited website and used protocol. Such attacks are called traffic analysis. Proposed countermeasures attempt to change the distribution of such features. however, either they fail to effectively reduce attacker's accuracy or do so while enforcing high bandwidth overhead and timing delay. In this paper, through the use of a predefined set of clustered traces of websites and a greedy packet morphing algorithm, we introduce a website fingerprinting countermeasure called TG-PSM. Firstly, this method clusters websites based on their behavior in different phases of loading. Secondly, it finds a suitable target site for any visiting website based on user indicated importance degree; thus providing dynamic tunability. Thirdly, this method morphs the given website to the target website using a greedy algorithm considering the distance and the resulted overhead. Our evaluations show that TG-PSM outperforms previous countermeasures regarding attacker accuracy reduction and enforced bandwidth, e.g., reducing bandwidth overhead over 40% while maintaining attacker's accuracy.

We study the problem of learning a mixture model of non-parametric product distributions. The problem of learning a mixture model is that of finding the component distributions along with the mixing weights using observed samples generated from the mixture. The problem is well-studied in the parametric setting, i.e., when the component distributions are members of a parametric family -- such as Gaussian distributions. In this work, we focus on multivariate mixtures of non-parametric product distributions and propose a two-stage approach which recovers the component distributions of the mixture under a smoothness condition. Our approach builds upon the identifiability properties of the canonical polyadic (low-rank) decomposition of tensors, in tandem with Fourier and Shannon-Nyquist sampling staples from signal processing. We demonstrate the effectiveness of the approach on synthetic and real datasets.

The study of healthy brain development helps to better understand the brain transformation and brain connectivity patterns which happen during childhood to adulthood. This study presents a sparse machine learning solution across whole-brain functional connectivity (FC) measures of three sets of data, derived from resting state functional magnetic resonance imaging (rs-fMRI) and task fMRI data, including a working memory n-back task (nb-fMRI) and an emotion identification task (em-fMRI). These multi-modal image data are collected on a sample of adolescents from the Philadelphia Neurodevelopmental Cohort (PNC) for the prediction of brain ages. Due to extremely large variable-to-instance ratio of PNC data, a high dimensional matrix with several irrelevant and highly correlated features is generated and hence a pattern learning approach is necessary to extract significant features. We propose a sparse learner based on the residual errors along the estimation of an inverse problem for the extreme learning machine (ELM) neural network. The purpose of the approach is to overcome the overlearning problem through pruning of several redundant features and their corresponding output weights. The proposed multimodal sparse ELM classifier based on residual errors (RES-ELM) is highly competitive in terms of the classification accuracy compared to its counterparts such as conventional ELM, and sparse Bayesian learning ELM.