Multi-layered representation is believed to be the key ingredient of deep neural networks especially in cognitive tasks like computer vision. While non-differentiable models such as gradient boosting decision trees (GBDTs) are the dominant methods for modeling discrete or tabular data, they are hard to incorporate with such representation learning ability. In this work, we propose the multi-layered GBDT forest (mGBDTs), with an explicit emphasis on exploring the ability to learn hierarchical representations by stacking several layers of regression GBDTs as its building block. The model can be jointly trained by a variant of target propagation across layers, without the need to derive back-propagation nor differentiability. Experiments and visualizations confirmed the effectiveness of the model in terms of performance and representation learning ability.

This paper analyzes asymptotic performance of a regularized multi-task learning model where task parameters are optimized jointly. If tasks are closely related, empirical work suggests multi-task learning models to outperform single-task ones in finite sample cases. As data size grows indefinitely, we show the learned multi-classifier to optimize an average misclassification error function which depicts the risk of applying multi-task learning algorithm to making decisions. This technique conclusion demonstrates the regularized multi-task learning model to be able to produce reliable decision rule for each task in the sense that it will asymptotically converge to the corresponding Bayes rule. Also, we find the interaction effect between tasks vanishes as data size growing indefinitely, which is quite different from the behavior in finite sample cases.

Private business schools in India face a common problem of selecting quality students for their MBA programs to achieve desired placement percentage. Business school data set is biased towards one class, i.e., imbalanced in nature. And learning from imbalanced data set is a difficult proposition. Most existing classification methods tend not to perform well on minority class examples when the data set is extremely imbalanced, because they aim to optimize the overall accuracy without considering the relative distribution of each class. The aim of the paper is twofold. We first propose an integrated sampling technique with an ensemble of classification tree (CT) and artificial neural network (ANN) model as one of the methodologies which works better compared to other similar methods. Further we propose a superensemble imbalanced classifier which works better on the original business school data set. Our proposed superensemble classifier not only handles the imbalance data set but also achieves higher accuracy in case of feature selection cum classification problems. The proposal has been compared with other state-of-the-art classifiers and found to be very competitive.

The representation power of similarity functions used in neural network-based graph embedding is considered. The inner product similarity (IPS) with feature vectors computed via neural networks is commonly used for representing the strength of association between two nodes. However, only a little work has been done on the representation capability of IPS. A very recent work shed light on the nature of IPS and reveals that IPS has the capability of approximating any positive definite (PD) similarities. However, a simple example demonstrates the fundamental limitation of IPS to approximate non-PD similarities. We then propose a novel model named Shifted IPS (SIPS) that approximates any Conditionally PD (CPD) similarities arbitrary well. CPD is a generalization of PD with many examples such as negative Poincare distance and negative Wasserstein distance, thus SIPS has a potential impact to significantly improve the applicability of graph embedding without taking great care in configuring the similarity function. Our numerical experiments demonstrate the SIPS's superiority over IPS. In theory, we further extend SIPS beyond CPD by considering the inner product in Minkowski space so that it approximates more general similarities.

Active Learning (AL) requires learners to retrain the classifier with the minimum human supervisions or labeling in the unlabeled data pool when the current training set is not enough. However, general AL sampling strategies with a few label support inevitably suffer from performance decrease. To identify which samples determine the performance of the classification hyperplane, Core Vector Machine (CVM) and Ball Vector Machine (BVM) use the geometry boundary points of each Minimum Enclosing Ball (MEB) to train the classification hypothesis. Their theoretical analysis and experimental results show that the improved classifiers not only converge faster but also obtain higher accuracies compared with Support Vector Machine (SVM). Inspired by this, we formulate the cluster boundary point detection issue as the MEB boundary problem after presenting a convincing proof of this observation. Because the enclosing ball boundary may have a high fitting ratio when it can not enclose the class tightly, we split the global ball problem into two kinds of small Local Minimum Enclosing Ball (LMEB): Boundary ball (B-ball) and Core ball (C-ball) to tackle its over-fitting problem. Through calculating the update of radius and center when extending the local ball space, we adopt the minimum update ball to obtain the geometric update optimization scheme of B-ball and C-ball. After proving their update relationship, we design the LEB (Local Enclosing Ball) algorithm using centers of B-ball of each class to detect the enclosing ball boundary points for AL sampling. Experimental and theoretical studies have shown that the classification accuracy, time, and space performance of our proposed method significantly are superior than the state-of-the-art algorithms.

In this paper, we study the problem of distributed multi-agent optimization over a network, where each agent possesses a local cost function that is smooth and strongly convex. The global objective is to find a common solution that minimizes the average of all cost functions. Assuming agents only have access to unbiased estimates of the gradients of their local cost functions, we consider a distributed stochastic gradient tracking method (DSGT) and a gossip-like stochastic gradient tracking method (GSGT). We show that, in expectation, the iterates generated by each agent are attracted to a neighborhood of the optimal solution, where they accumulate exponentially fast (under a constant stepsize choice). Under DSGT, the limiting (expected) error bounds on the distance of the iterates from the optimal solution decrease with the network size $n$, which is a comparable performance to a centralized stochastic gradient algorithm. Moreover, we show that when the network is well-connected, GSGT incurs lower communication cost than DSGT while maintaining a similar computational cost. Numerical example further demonstrates the effectiveness of the proposed methods.

Area under the receiver operating characteristics curve (AUC) is an important metric for a wide range of signal processing and machine learning problems, and scalable methods for optimizing AUC have recently been proposed. However, handling very large datasets remains an open challenge for this problem. This paper proposes a novel approach to AUC maximization, based on sampling mini-batches of positive/negative instance pairs and computing U-statistics to approximate a global risk minimization problem. The resulting algorithm is simple, fast, and learning-rate free. We show that the number of samples required for good performance is independent of the number of pairs available, which is a quadratic function of the positive and negative instances. Extensive experiments show the practical utility of the proposed method.

Stochastic gradient descent is the method of choice for large scale optimization of machine learning objective functions. Yet, its performance is greatly variable and heavily depends on the choice of the stepsizes. This has motivated a large body of research on adaptive stepsizes. However, there is currently a gap in our theoretical understanding of these methods, especially in the non-convex setting. In this paper, we start closing this gap: we theoretically analyze the use of adaptive stepsizes, like the ones in AdaGrad, in the non-convex setting. We show sufficient conditions for almost sure convergence to a stationary point when the adaptive stepsizes are used, proving the first guarantee for AdaGrad in the non-convex setting. Moreover, we show explicit rates of convergence that automatically interpolates between $O(1/T)$ and $O(1/\sqrt{T})$ depending on the noise of the stochastic gradients, in both the convex and non-convex setting.

Kernel Methods Next Generation (KMNG) introduces a framework to use kernel approximates in the mini-batch setting with SGD Optimizer as an alternative to Deep Learning. McKernel is a C++ library for KMNG ML Large-scale. It contains a CPU optimized implementation of the Fastfood algorithm that allows the computation of approximated kernel expansions in log-linear time. The algorithm requires to compute the product of Walsh Hadamard Transform (WHT) matrices. A cache friendly SIMD Fast Walsh Hadamard Transform (FWHT) that achieves compelling speed and outperforms current state-of-the-art methods has been developed. McKernel allows to obtain non-linear classification combining Fastfood and a linear classifier.

We'll find weather data, explore it and get it in order. We'll use the modeling tools of deseasonalization and linear regression to predict temperatures at the beach. We'll use the statistical tools of autoregression and confidence intervals to guide our feature selection and apply our results. And we'll code the whole thing up from scratch in python and organize it to be easy to read and easy to extend. When you're done, you'll have a standalone weather predictor that can estimate high temperatures three days from now.