Online Training of LSTM Networks in Distributed Systems for Variable Length Data Sequences.

In this brief, we investigate online training of long short term memory (LSTM) architectures in a distributed network of nodes, where each node employs an LSTM-based structure for online regression. In particular, each node sequentially receives a variable length data sequence with its label and can only exchange information with its neighbors to train the LSTM architecture. We first provide a generic LSTM-based regression structure for each node. In order to train this structure, we put the LSTM equations in a nonlinear state-space form for each node and then introduce a highly effective and efficient distributed particle filtering (DPF)-based training algorithm. We also introduce a distributed extended Kalman filtering-based training algorithm for comparison. Here, our DPF-based training algorithm guarantees convergence to the performance of the optimal LSTM coefficients in the mean square error sense under certain conditions. We achieve this performance with communication and computational complexity in the order of the first-order gradient-based methods. Through both simulated and real-life examples, we illustrate significant performance improvements with respect to the state-of-the-art methods.

Online Density Estimation of Nonstationary Sources Using Exponential Family of Distributions.

We investigate online probability density estimation (or learning) of nonstationary (and memoryless) sources using exponential family of distributions. To this end, we introduce a truly sequential algorithm that achieves Hannan-consistent log-loss regret performance against true probability distribution without requiring any information about the observation sequence (e.g., the time horizon $T$ and the drift of the underlying distribution $C$ ) to optimize its parameters. Our results are guaranteed to hold in an individual sequence manner. Our log-loss performance with respect to the true probability density has regret bounds of $O(({CT})^{1/2})$ , where $C$ is the total change (drift) in the natural parameters of the underlying distribution. To achieve this, we design a variety of probability density estimators with exponentially quantized learning rates and merge them with a mixture-of-experts notion. Hence, we achieve this square-root regret with computational complexity only logarithmic in the time horizon. Thus, our algorithm can be efficiently used in big data applications. Apart from the regret bounds, through synthetic and real-life experiments, we demonstrate substantial performance gains with respect to the state-of-the-art probability density estimation algorithms in the literature.

A unified approach to universal prediction: generalized upper and lower bounds.

We study sequential prediction of real-valued, arbitrary, and unknown sequences under the squared error loss as well as the best parametric predictor out of a large, continuous class of predictors. Inspired by recent results from computational learning theory, we refrain from any statistical assumptions and define the performance with respect to the class of general parametric predictors. In particular, we present generic lower and upper bounds on this relative performance by transforming the prediction task into a parameter learning problem. We first introduce the lower bounds on this relative performance in the mixture of experts framework, where we show that for any sequential algorithm, there always exists a sequence for which the performance of the sequential algorithm is lower bounded by zero. We then introduce a sequential learning algorithm to predict such arbitrary and unknown sequences, and calculate upper bounds on its total squared prediction error for every bounded sequence. We further show that in some scenarios, we achieve matching lower and upper bounds, demonstrating that our algorithms are optimal in a strong minimax sense such that their performances cannot be improved further. As an interesting result, we also prove that for the worst case scenario, the performance of randomized output algorithms can be achieved by sequential algorithms so that randomized output algorithms do not improve the performance.

Data imputation through the identification of local anomalies.

We introduce a comprehensive and statistical framework in a model free setting for a complete treatment of localized data corruptions due to severe noise sources, e.g., an occluder in the case of a visual recording. Within this framework, we propose: 1) a novel algorithm to efficiently separate, i.e., detect and localize, possible corruptions from a given suspicious data instance and 2) a maximum a posteriori estimator to impute the corrupted data. As a generalization to Euclidean distance, we also propose a novel distance measure, which is based on the ranked deviations among the data attributes and empirically shown to be superior in separating the corruptions. Our algorithm first splits the suspicious instance into parts through a binary partitioning tree in the space of data attributes and iteratively tests those parts to detect local anomalies using the nominal statistics extracted from an uncorrupted (clean) reference data set. Once each part is labeled as anomalous versus normal, the corresponding binary patterns over this tree that characterize corruptions are identified and the affected attributes are imputed. Under a certain conditional independency structure assumed for the binary patterns, we analytically show that the false alarm rate of the introduced algorithm in detecting the corruptions is independent of the data and can be directly set without any parameter tuning. The proposed framework is tested over several well-known machine learning data sets with synthetically generated corruptions and experimentally shown to produce remarkable improvements in terms of classification purposes with strong corruption separation capabilities. Our experiments also indicate that the proposed algorithms outperform the typical approaches and are robust to varying training phase conditions.

A Deterministic Analysis of an Online Convex Mixture of Experts Algorithm.

We analyze an online learning algorithm that adaptively combines outputs of two constituent algorithms (or the experts) running in parallel to estimate an unknown desired signal. This online learning algorithm is shown to achieve and in some cases outperform the mean-square error (MSE) performance of the best constituent algorithm in the steady state. However, the MSE analysis of this algorithm in the literature uses approximations and relies on statistical models on the underlying signals. Hence, such an analysis may not be useful or valid for signals generated by various real-life systems that show high degrees of nonstationarity, limit cycles and that are even chaotic in many cases. In this brief, we produce results in an individual sequence manner. In particular, we relate the time-accumulated squared estimation error of this online algorithm at any time over any interval to the one of the optimal convex mixture of the constituent algorithms directly tuned to the underlying signal in a deterministic sense without any statistical assumptions. In this sense, our analysis provides the transient, steady-state, and tracking behavior of this algorithm in a strong sense without any approximations in the derivations or statistical assumptions on the underlying signals such that our results are guaranteed to hold. We illustrate the introduced results through examples.

Embedding and retrieving private metadata in electrocardiograms.

Due to the recent explosion of 'identity theft' cases, the safeguarding of private data has been the focus of many scientific efforts. Medical data contain a number of sensitive attributes, whose access the rightful owner would ideally like to disclose only to authorized personnel. One way of providing limited access to sensitive data is through means of encryption. In this work we follow a different path, by proposing the fusion of the sensitive metadata within the medical data. Our work is focused on medical time-series signals and in particular on Electrocardiograms (ECG). We present techniques that allow the embedding and retrieval of sensitive numerical data, such as the patient's social security number or birth date, within the medical signal. The proposed technique not only allows the effective hiding of the sensitive metadata within the signal itself, but it additionally provides a way of authenticating the data ownership or providing assurances about the origin of the data. Our methodology builds upon watermarking notions, and presents the following desirable characteristics: (a) it does not distort important ECG characteristics, which are essential for proper medical diagnosis, (b) it allows not only the embedding but also the efficient retrieval of the embedded data, (c) it provides resilience and fault tolerance by employing multistage watermarks (both robust and fragile). Our experiments on real ECG data indicate the viability of the proposed scheme.