To improve the classification performance in the context of hyperspectral image processing, many works have been developed based on two common strategies, namely the spatial-spectral information integration and the utilization of neural networks. However, both strategies typically require more training data than the classical algorithms, aggregating the shortage of labeled samples. In this paper, we propose a novel framework that organically combines an existing spectrum-based deep metric learning model and the conditional random field algorithm. The deep metric learning model is supervised by center loss, and is used to produce spectrum-based features that gather more tightly within classes in Euclidean space. The conditional random field with Gaussian edge potentials, which is firstly proposed for image segmentation problem, is utilized to jointly account for both the geometry distance of two pixels and the Euclidean distance between their corresponding features extracted by the deep metric learning model. The final predictions are given by the conditional random field. Generally, the proposed framework is trained by spectra pixels at the deep metric learning stage, and utilizes the half handcrafted spatial features at the conditional random field stage. This settlement alleviates the shortage of training data to some extent. Experiments on two real hyperspectral images demonstrate the advantages of the proposed method in terms of both classification accuracy and computation cost.

This paper combines data-driven and model-driven methods for real-time misinformation detection. Our algorithm, named QuickStop, is an optimal stopping algorithm based on a probabilistic information spreading model obtained from labeled data. The algorithm consists of an offline machine learning algorithm for learning the probabilistic information spreading model and an online optimal stopping algorithm to detect misinformation. The online detection algorithm has both low computational and memory complexities. Our numerical evaluations with a real-world dataset show that QuickStop outperforms existing misinformation detection algorithms in terms of both accuracy and detection time (number of observations needed for detection). Our evaluations with synthetic data further show that QuickStop is robust to (offline) learning errors.

We study data poisoning attacks in the online learning setting where the training items stream in one at a time, and the adversary perturbs the current training item to manipulate present and future learning. In contrast, prior work on data poisoning attacks has focused on either batch learners in the offline setting, or online learners but with full knowledge of the whole training sequence. We show that online poisoning attack can be formulated as stochastic optimal control, and provide several practical attack algorithms based on control and deep reinforcement learning. Extensive experiments demonstrate the effectiveness of the attacks.

We study stochastic gradient descent {\em without replacement} (\sgdwor) for smooth convex functions. \sgdwor is widely observed to converge faster than true \sgd where each sample is drawn independently {\em with replacement}~\cite{bottou2009curiously} and hence, is more popular in practice. But it's convergence properties are not well understood as sampling without replacement leads to coupling between iterates and gradients. By using method of exchangeable pairs to bound Wasserstein distance, we provide the first non-asymptotic results for \sgdwor when applied to {\em general smooth, strongly-convex} functions. In particular, we show that \sgdwor converges at a rate of $O(1/K^2)$ while \sgd~is known to converge at $O(1/K)$ rate, where $K$ denotes the number of passes over data and is required to be {\em large enough}. Existing results for \sgdwor in this setting require additional {\em Hessian Lipschitz assumption}~\cite{gurbuzbalaban2015random,haochen2018random}. For {\em small} $K$, we show \sgdwor can achieve same convergence rate as \sgd for {\em general smooth strongly-convex} functions. Existing results in this setting require $K=1$ and hold only for generalized linear models \cite{shamir2016without}. In addition, by careful analysis of the coupling, for both large and small $K$, we obtain better dependence on problem dependent parameters like condition number.

When the weights in a particle filter are not available analytically, standard resampling methods cannot be employed. To circumvent this problem state-of-the-art algorithms replace the true weights with non-negative unbiased estimates. This algorithm is still valid but at the cost of higher variance of the resulting filtering estimates in comparison to a particle filter using the true weights. We propose here a novel algorithm that allows for resampling according to the true intractable weights when only an unbiased estimator of the weights is available. We demonstrate our algorithm on several examples.

The Straight-Through Estimator (STE) is widely used for back-propagating gradients through the quantization function, but the STE technique lacks a complete theoretical understanding. We propose an alternative methodology called alpha-blending (AB), which quantizes neural networks to low-precision using stochastic gradient descent (SGD). Our method (AB) avoids STE approximation by replacing the quantized weight in the loss function by an affine combination of the quantized weight w_q and the corresponding full-precision weight w with non-trainable scalar coefficient $\alpha$ and $1-\alpha$. During training, $\alpha$ is gradually increased from 0 to 1; the gradient updates to the weights are through the full-precision term, $(1-\alpha)w$, of the affine combination; the model is converted from full-precision to low-precision progressively. To evaluate the method, a 1-bit BinaryNet on CIFAR10 dataset and 8-bits, 4-bits MobileNet v1, ResNet_50 v1/2 on ImageNet dataset are trained using the alpha-blending approach, and the evaluation indicates that AB improves top-1 accuracy by 0.9%, 0.82% and 2.93% respectively compared to the results of STE based quantization.

The preponderance of connected devices provides unprecedented opportunities for fine-grained monitoring of the public infrastructure. However while classical models expect high quality application-specific data streams, the promise of the Internet of Things (IoT) is that of an abundance of disparate and noisy datasets from connected devices. In this context, we consider the problem of estimation of the level of service of a city-wide public transport network. We first propose a robust unsupervised model for train movement inference from wifi traces, via the application of robust clustering methods to a one dimensional spatio-temporal setting. We then explore the extent to which the demand-supply gap can be estimated from connected devices. We propose a classification model of real-time commuter patterns, including both a batch training phase and an online learning component. We describe our deployment architecture and assess our system accuracy on a large-scale anonymized dataset comprising more than 10 billion records.

Classifiers label data as belonging to one of a set of groups based on input features. It is challenging to obtain accurate classification performance when the feature distributions in the different classes are complex, with nonlinear, overlapping and intersecting supports. This is particularly true when training data are limited. To address this problem, this article proposes a new type of classifier based on obtaining a local approximation to the support of the data within each class in a neighborhood of the feature to be classified, and assigning the feature to the class having the closest support. This general algorithm is referred to as LOcal Manifold Approximation (LOMA) classification. As a simple and theoretically supported special case having excellent performance in a broad variety of examples, we use spheres for local approximation, obtaining a SPherical Approximation (SPA) classifier. We illustrate substantial gains for SPA over competitors on a variety of challenging simulated and real data examples.

The Expectation-Maximization (EM) algorithm is one of the most popular methods used to solve the problem of distribution-based clustering in unsupervised learning. In this paper, we propose an analysis of a generalized EM (GEM) algorithm and a designed EM-like algorithm, as linear time-invariant (LTI) systems with a feedback nonlinearity, and by leveraging tools from robust control theory, particularly integral quadratic constraints (IQCs). Towards this goal, we investigate the absolute stability of dynamical systems of the above form with a sector-bounded feedback nonlinearity, that represent the aforementioned algorithms. This analysis allows us to craft a strongly convex objective function, which led to the design of the aforementioned novel EM-like algorithm for Gaussian mixture models (GMMs). Furthermore, it allows us to establish bounds on the convergence rates of the studied algorithms. In particular, the derived bounds for our proposed EM-like algorithm generalize bounds found in the literature for the EM algorithm on GMMs, and our analysis of an existing gradient ascent GEM algorithm based on the $Q$-function allowed us to approximately recover bounds found in the literature.

Spatio-temporal prediction plays an important role in many application areas especially in traffic domain. However, due to complicated spatio-temporal dependency and high non-linear dynamics in road networks, traffic prediction task is still challenging. Existing works either exhibit heavy training cost or fail to accurately capture the spatio-temporal patterns, also ignore the correlation between distant roads that share the similar patterns. In this paper, we propose a novel deep learning framework to overcome these issues: 3D Temporal Graph Convolutional Networks (3D-TGCN). Two novel components of our model are introduced. (1) Instead of constructing the road graph based on spatial information, we learn it by comparing the similarity between time series for each road, thus providing a spatial information free framework. (2) We propose an original 3D graph convolution model to model the spatio-temporal data more accurately. Empirical results show that 3D-TGCN could outperform state-of-the-art baselines.