We consider the problem of reconstructing the internal structure of an object from limited x-ray projections. In this work, we use a Gaussian process to model the target function. In contrast to other established methods, this comes with the advantage of not requiring any manual parameter tuning, which usually arises in classical regularization strategies. The Gaussian process is well-known in a heavy computation for the inversion of a covariance matrix, and in this work, by employing an approximative spectral-based technique, we reduce the computational complexity and avoid the need of numerical integration. Results from simulated and real data indicate that this approach is less sensitive to streak artifacts as compared to the commonly used method of filteredback projection, an analytic reconstruction algorithm using Radon inversion formula.

Differentially private learning has recently emerged as the leading approach for privacy-preserving machine learning. Differential privacy can complicate learning procedures because each access to the data needs to be carefully designed and carries a privacy cost. For example, standard parameter tuning with a validation set cannot be easily applied. In this paper, we propose a differentially private algorithm for the adaptation of the learning rate for differentially private stochastic gradient descent (SGD) that avoids the need for validation set use. The idea for the adaptiveness comes from the technique of extrapolation in classical numerical analysis: to get an estimate for the error against the gradient flow which underlies SGD, we compare the result obtained by one full step and two half-steps. We prove the privacy of the method using the moments accountant mechanism. This allows us to compute tight privacy bounds. Empirically we show that our method is competitive with manually tuned commonly used optimisation methods for training deep neural networks and differentially private variational inference.

We propose an effective method for creating interpretable control agents, by re-purposing the function of a biological neural circuit model, to govern simulated and real world reinforcement learning (RL) test-beds. Inspired by the structure of the nervous system of the soil-worm, C. elegans, we introduce Neuronal Circuit Policies (NCPs) as a novel recurrent neural network instance with liquid time-constants, universal approximation capabilities and interpretable dynamics. We theoretically show that they can approximate any finite simulation time of a given continuous n-dimensional dynamical system, with n output units and some hidden units. We model instances of the policies and learn their synaptic and neuronal parameters to control standard RL tasks and demonstrate its application for autonomous parking of a real rover robot on a predefined trajectory. For reconfiguration of the purpose of the neural circuit, we adopt a search-based RL algorithm. We show that our neuronal circuit policies perform as good as deep neural network policies with the advantage of realizing interpretable dynamics at the cell-level. We theoretically find bounds for the time-varying dynamics of the circuits, and introduce a novel way to reason about networks' dynamics.

This paper addresses the problem of change-point detection on sequences of high-dimensional and heterogeneous observations, which also possess a periodic temporal structure. Due to the dimensionality problem, when the time between change-points is on the order of the dimension of the model parameters, drifts in the underlying distribution can be misidentified as changes. To overcome this limitation we assume that the observations lie in a lower dimensional manifold that admits a latent variable representation. In particular, we propose a hierarchical model that is computationally feasible, widely applicable to heterogeneous data and robust to missing instances. Additionally, to deal with the observations' periodic dependencies, we employ a circadian model where the data periodicity is captured by non-stationary covariance functions. We validate the proposed technique on synthetic examples and we demonstrate its utility in the detection of changes for human behavior characterization.

Recently, a wide range of smart devices are deployed in a variety of environments to improve the quality of human life. One of the important IoT-based applications is smart homes for healthcare, especially for elders. IoT-based smart homes enable elders' health to be properly monitored and taken care of. However, elders' privacy might be disclosed from smart homes due to non-fully protected network communication or other reasons. To demonstrate how serious this issue is, we introduce in this paper a Privacy Mining Approach (PMA) to mine privacy from smart homes by conducting a series of deductions and analyses on sensor datasets generated by smart homes. The experimental results demonstrate that PMA is able to deduce a global sensor topology for a smart home and disclose elders' privacy in terms of their house layouts.

-- A deep learning network was used to predict future blood glucose levels, as this can permit diabetes patients to take action before imminent hyperglycaemia and hypoglycaemia. A sequential model with one long-short-term memory (LSTM) layer, one bidirectional LSTM layer and several fully connected layers was used to predict blood glucose levels for different prediction horizons. The method was trained and tested on 26 datasets from 20 real patients. The proposed network outperforms the baseline methods in terms of all evaluation criteria. Diabetes can be mainly classified into Type 1 diabetes (T1D) and Type 2 diabetes (T2D), where the former is caused by destruction of the pancreatic beta cells resulting in insulin deficiency, while the latter due to the ineffective use of insulin.

Stochastic gradient methods are the workhorse (algorithms) of large-scale optimization problems in machine learning, signal processing, and other computational sciences and engineering. This paper studies Markov chain gradient descent, a variant of stochastic gradient descent where the random samples are taken on the trajectory of a Markov chain. Existing results of this method assume convex objectives and a reversible Markov chain and thus have their limitations. We establish new non-ergodic convergence under wider step sizes, for nonconvex problems, and for non-reversible finite-state Markov chains. Nonconvexity makes our method applicable to broader problem classes. Non-reversible finite-state Markov chains, on the other hand, can mix substatially faster. To obtain these results, we introduce a new technique that varies the mixing levels of the Markov chains. The reported numerical results validate our contributions.

We show that many machine learning goals, such as improved fairness metrics, can be expressed as constraints on the model's predictions, which we call rate constraints. We study the problem of training non-convex models subject to these rate constraints (or any non-convex and non-differentiable constraints). In the non-convex setting, the standard approach of Lagrange multipliers may fail. Furthermore, if the constraints are non-differentiable, then one cannot optimize the Lagrangian with gradient-based methods. To solve these issues, we introduce the proxy-Lagrangian formulation. This new formulation leads to an algorithm that produces a stochastic classifier by playing a two-player non-zero-sum game solving for what we call a semi-coarse correlated equilibrium, which in turn corresponds to an approximately optimal and feasible solution to the constrained optimization problem. We then give a procedure which shrinks the randomized solution down to one that is a mixture of at most $m+1$ deterministic solutions, given $m$ constraints. This culminates in algorithms that can solve non-convex constrained optimization problems with possibly non-differentiable and non-convex constraints with theoretical guarantees. We provide extensive experimental results enforcing a wide range of policy goals including different fairness metrics, and other goals on accuracy, coverage, recall, and churn.

A network embedding consists of a vector representation for each node in the network. Network embeddings have shown their usefulness in node classification and visualization in many real-world application domains, such as social networks and web networks. While directed networks with text associated with each node, such as citation networks and software package dependency networks, are commonplace, to the best of our knowledge, their embeddings have not been specifically studied. In this paper, we create PCT ADW-1 and PCT ADW-2, two algorithms based on NNs that learn em-beddings of directed networks with text associated with each node. We create two new labeled directed networks with text-associated node: The package dependency networks in two popular GNU/Linux distributions, Debian and Fedora. We experimentally demonstrate that the embeddings produced by our NNs resulted in node classification with better quality than those of various baselines on these two networks. We observe that there exist systematic presence of analogies (similar to those in word embeddings) in the network embed-dings of software package dependency networks. To the best of our knowledge, this is the first time that such a systematic presence of analogies is observed in network and document embeddings. This may potentially open up a new venue for better understanding networks and documents algorith-mically using their embeddings as well as for better human understanding of network and document embeddings.

Forecasting multivariate time series data, such as prediction of electricity consumption, solar power production, and polyphonic piano pieces, has numerous valuable applications. However, complex and non-linear interdependencies between time steps and series complicate the task. To obtain accurate prediction, it is crucial to model long-term dependency in time series data, which can be achieved to some good extent by recurrent neural network (RNN) with attention mechanism. Typical attention mechanism reviews the information at each previous time step and selects the relevant information to help generate the outputs, but it fails to capture the temporal patterns across multiple time steps. In this paper, we propose to use a set of filters to extract time-invariant temporal patterns, which is similar to transforming time series data into its "frequency domain". Then we proposed a novel attention mechanism to select relevant time series, and use its "frequency domain" information for forecasting. We applied the proposed model on several real-world tasks and achieved the state-of-the-art performance in all of them with only one exception. We also show that to some degree the learned filters play the role of bases in discrete Fourier transform.