This paper presents an acceleration framework for packing linear programming problems where the amount of data available is limited, i.e., where the number of constraints m is small compared to the variable dimension n. The framework can be used as a black box to speed up linear programming solvers dramatically, by two orders of magnitude in our experiments. We present worst-case guarantees on the quality of the solution and the speedup provided by the algorithm, showing that the framework provides an approximately optimal solution while running the original solver on a much smaller problem. The framework can be used to accelerate exact solvers, approximate solvers, and parallel/distributed solvers. Further, it can be used for both linear programs and integer linear programs.

We propose a test of independence of two multivariate random vectors, given a sample from the underlying population. Our approach, which we call MINT, is based on the estimation of mutual information, whose decomposition into joint and marginal entropies facilitates the use of recently-developed efficient entropy estimators derived from nearest neighbour distances. The proposed critical values, which may be obtained from simulation (in the case where one marginal is known) or resampling, guarantee that the test has nominal size, and we provide local power analyses, uniformly over classes of densities whose mutual information satisfies a lower bound. Our ideas may be extended to provide a new goodness-of-fit tests of normal linear models based on assessing the independence of our vector of covariates and an appropriately-defined notion of an error vector. The theory is supported by numerical studies on both simulated and real data.

In this paper, we consider the problem of machine teaching, the inverse problem of machine learning. Different from traditional machine teaching which views the learners as batch algorithms, we study a new paradigm where the learner uses an iterative algorithm and a teacher can feed examples sequentially and intelligently based on the current performance of the learner. We show that the teaching complexity in the iterative case is very different from that in the batch case. Instead of constructing a minimal training set for learners, our iterative machine teaching focuses on achieving fast convergence in the learner model. Depending on the level of information the teacher has from the learner model, we design teaching algorithms which can provably reduce the number of teaching examples and achieve faster convergence than learning without teachers.

Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component does not explicitly encourage discriminative learning of features. In this paper, we propose a generalized large-margin softmax (L-Softmax) loss which explicitly encourages intra-class compactness and inter-class separability between learned features. Moreover, L-Softmax not only can adjust the desired margin but also can avoid overfitting. We also show that the L-Softmax loss can be optimized by typical stochastic gradient descent. Extensive experiments on four benchmark datasets demonstrate that the deeply-learned features with L-softmax loss become more discriminative, hence significantly boosting the performance on a variety of visual classification and verification tasks.

We present an information-theoretic framework for bounding the number of labeled samples needed to train a classifier in a parametric Bayesian setting. We derive bounds on the average $L_p$ distance between the learned classifier and the true maximum a posteriori classifier, which are well-established surrogates for the excess classification error due to imperfect learning. We provide lower and upper bounds on the rate-distortion function, using $L_p$ loss as the distortion measure, of a maximum a priori classifier in terms of the differential entropy of the posterior distribution and a quantity called the interpolation dimension, which characterizes the complexity of the parametric distribution family. In addition to expressing the information content of a classifier in terms of lossy compression, the rate-distortion function also expresses the minimum number of bits a learning machine needs to extract from training data to learn a classifier to within a specified $L_p$ tolerance. We use results from universal source coding to express the information content in the training data in terms of the Fisher information of the parametric family and the number of training samples available. The result is a framework for computing lower bounds on the Bayes $L_p$ risk. This framework complements the well-known probably approximately correct (PAC) framework, which provides minimax risk bounds involving the Vapnik-Chervonenkis dimension or Rademacher complexity. Whereas the PAC framework provides upper bounds the risk for the worst-case data distribution, the proposed rate-distortion framework lower bounds the risk averaged over the data distribution. We evaluate the bounds for a variety of data models, including categorical, multinomial, and Gaussian models. In each case the bounds are provably tight orderwise, and in two cases we prove that the bounds are tight up to multiplicative constants.

In this post we are going to develop an application for the purpose of detecting spam emails.The algorithm which will be used is Logistic Regression, implementation from SPARK MLib. No deep knowledge on the field is required as the topics are described from a high level perspective as possible. Full working code is provided together with a running application for further experiments on your choice of emails(please last section). Logistic Regression is an algorithm used for classification problems. In Classification problems we are given a lot of labeled data(example spam and not spam) and when a new example is coming we want to know which category it belongs to.

One of the major aspects of training your machine learning model is avoiding overfitting. The model will have a low accuracy if it is overfitting. This happens because your model is trying too hard to capture the noise in your training dataset. By noise we mean the data points that don't really represent the true properties of your data, but random chance. Learning such data points, makes your model more flexible, at the risk of overfitting. The concept of balancing bias and variance, is helpful in understanding the phenomenon of overfitting.

The lack of interpretability remains a key barrier to the adoption of deep models in many applications. In this work, we explicitly regularize deep models so human users might step through the process behind their predictions in little time. Specifically, we train deep time-series models so their class-probability predictions have high accuracy while being closely modeled by decision trees with few nodes. Using intuitive toy examples as well as medical tasks for treating sepsis and HIV, we demonstrate that this new tree regularization yields models that are easier for humans to simulate than simpler L1 or L2 penalties without sacrificing predictive power.

HE problem of training a machine learning model in the presence of different training and test distributions is known as domain adaptation [3], [6]-[9]. The goal of domain adaptation is to build a model that performs well on a target distribution while it is trained on a different but related source distribution. One important example is in the sentiment analysis of product reviews [1], where a model is trained on data of a source product category, e. g. kitchen appliances, and it is tested on data of a related category, e. g. books. A second example is the training of image classifiers on unlabeled real images by means of nearly-synthetic images that are fully labeled but which have a distribution that is different [2], [3]. Another example is the content-based depth range adaptation of unlabeled stereoscopic videos by means of labeled data from movies [4], [5]. It is shown in [10], that a classifier's error on the target domain can be bounded in terms of its error on the source domain and a difference between the source and the target domain distribution [10]. This motivated many approaches to first extract features that overcome the distribution difference and subsequently minimize the source error [8], [11]-[13]. With the recent developments in representation learning, approaches have been developed that embed domain adaptation in the feature learning process.

Anomaly detection has numerous applications and has been studied vastly. We consider a complementary problem that has a much sparser literature: anomaly description. Interpretation of anomalies is crucial for practitioners for sense-making, troubleshooting, and planning actions. To this end, we present a new approach called x-PACS (for eXplaining Patterns of Anomalies with Characterizing Subspaces), which "reverse-engineers" the known anomalies by identifying (1) the groups (or patterns) that they form, and (2) the characterizing subspace and feature rules that separate each anomalous pattern from normal instances. Explaining anomalies in groups not only saves analyst time and gives insight into various types of anomalies, but also draws attention to potentially critical, repeating anomalies. In developing x-PACS, we first construct a desiderata for the anomaly description problem. From a descriptive data mining perspective, our method exhibits five desired properties in our desiderata. Namely, it can unearth anomalous patterns (i) of multiple different types, (ii) hidden in arbitrary subspaces of a high dimensional space, (iii) interpretable by the analysts, (iv) different from normal patterns of the data, and finally (v) succinct, providing the shortest data description. Furthermore, x-PACS is highly parallelizable and scales linearly in terms of data size. No existing work on anomaly description satisfies all of these properties simultaneously. While not our primary goal, the anomalous patterns we find serve as interpretable "signatures" and can be used for detection. We show the effectiveness of x-PACS in explanation as well as detection on real-world datasets as compared to state-of-the-art.