Generative adversarial nets (GANs) are widely used to learn the data sampling process and their performance may heavily depend on the loss functions, given a limited computational budget. This study revisits MMD-GAN that uses the maximum mean discrepancy (MMD) as the loss function for GAN and makes two contributions. First, we argue that the existing MMD loss function may discourage the learning of fine details in data as it attempts to contract the discriminator outputs of real data. To address this issue, we propose a repulsive loss function to actively learn the difference among the real data by simply rearranging the terms in MMD. Second, inspired by the hinge loss, we propose a bounded Gaussian kernel to stabilize the training of MMD-GAN with the repulsive loss function. The proposed methods are applied to the unsupervised image generation tasks on CIFAR-10, STL-10, CelebA, and LSUN bedroom datasets. Results show that the repulsive loss function significantly improves over the MMD loss at no additional computational cost and outperforms other representative loss functions. The proposed methods achieve an FID score of 16.21 on the CIFAR-10 dataset using a single DCGAN network and spectral normalization. Generative adversarial nets (GANs) (Goodfellow et al. (2014)) are a branch of generative models that learns to mimic the real data generating process. GANs have been intensively studied in recent years, with a variety of successful applications (Karras et al. (2018); Li et al. (2017b); Lai et al. (2017); Zhu et al. (2017); Ho & Ermon (2016)). The idea of GANs is to jointly train a generator network that attempts to produce artificial samples, and a discriminator network or critic that distinguishes the generated samples from the real ones. Compared to maximum likelihood based methods, GANs tend to produce samples with sharper and more vivid details but require more efforts to train. Recent studies on improving GAN training have mainly focused on designing loss functions, network architectures and training procedures. The loss function, or simply loss, defines quantitatively the difference of discriminator outputs between real and generated samples. The gradients of loss functions are used to train the generator and discriminator.

We derive explicit Mixed Integer Optimization (MIO) constraints, as opposed to iteratively imposing them in a cutting plane framework, that impose significance and avoid multicollinearity for building linear regression models. In this way we extend and improve the research program initiated in Bertsimas and King (2016) that imposes sparsity, robustness, pairwise collinearity and group sparsity explicitly and significance and avoiding multicollinearity iteratively. We present a variety of computational results on real and synthetic datasets that suggest that the proposed MIO has a significant computational edge compared to Bertsimas and King (2016) in accuracy, false detection rate and computational time in accounting for significance and multicollinearity as well as providing a holistic framework to produce regression models with desirable properties a priori.

We present a framework to train a structured prediction model by performing smoothing on the inference algorithm it builds upon. Smoothing overcomes the non-smoothness inherent to the maximum margin structured prediction objective, and paves the way for the use of fast primal gradient-based optimization algorithms. We illustrate the proposed framework by developing a novel primal incremental optimization algorithm for the structural support vector machine. The proposed algorithm blends an extrapolation scheme for acceleration and an adaptive smoothing scheme and builds upon the stochastic variance-reduced gradient algorithm. We establish its worst-case global complexity bound and study several practical variants, including extensions to deep structured prediction. We present experimental results on two real-world problems, namely named entity recognition and visual object localization. The experimental results show that the proposed framework allows us to build upon efficient inference algorithms to develop large-scale optimization algorithms for structured prediction which can achieve competitive performance on the two real-world problems.

Artificial Intelligence (AI) study and use is on the rise. Tools to enable AI are becoming more readily available, simpler to use and easier to implement. What's more is that the definition of AI itself has been broken down into ingredients that, when later applied into a recipe (or process), can provide multiple desired outcomes. One of the more important ingredients used in most recipes is Machine Learning. Machine Learning in essence is a way of teaching computers to provide more accurate predictions on provided data.

If you've been at machine learning long enough, you know that there is a "no free lunch" principle -- there's no one-size-fits-all algorithm that will help you solve every problem and tackle every dataset. I work for Springboard -- we've put a lot of research into machine learning training and resources. At Springboard, we offer the first online course with a machine learning job guarantee. What helps a lot when confronted with a new problem is to have a primer for what algorithm might be the best fit for certain situations. Here, we talk about different problems and data types and discuss what might be the most effective algorithm to try for each one, along with a resource that can help you implement that particular model.

The course rating is 4.5.

Abstract-- In this paper we propose the use of multiple local binary patterns(LBPs) to effectively classify land use images. We use the UC Merced 21 class land use image dataset. Task is challenging for classification as the dataset contains intra class variability and inter class similarities. Our proposed method of using multi-neighborhood LBPs combined with nearest neighbor classifier is able to achieve an accuracy of 77.76%. Further class wise analysis is conducted and suitable suggestion are made for further improvements to classification accuracy. INTRODUCTION The world is changing rapidly, new technology and infrastructure is resulting in faster growth. To meet the demands of the growing populations, cities are expanding and land use pattern are changing to accommodate the needs.

Recent work has shown that any classifier which classifies well under Gaussian noise can be leveraged to create a new classifier that is provably robust to adversarial perturbations in L2 norm. However, existing guarantees for such classifiers are suboptimal. In this work we provide the first tight analysis of this "randomized smoothing" technique. We then demonstrate that this extremely simple method outperforms by a wide margin all other provably L2-robust classifiers proposed in the literature. Furthermore, we train an ImageNet classifier with e.g. a provable top-1 accuracy of 49% under adversarial perturbations with L2 norm less than 0.5 (=127/255). No other provable adversarial defense has been shown to be feasible on ImageNet. While randomized smoothing with Gaussian noise only confers robustness in L2 norm, the empirical success of the approach suggests that provable methods based on randomization at test time are a promising direction for future research into adversarially robust classification. Code and trained models are available at https://github.com/locuslab/smoothing .

Recent years have witnessed an increased focus on interpretability and the use of machine learning to inform policy analysis and decision making. This paper applies machine learning to examine travel behavior and, in particular, on modeling changes in travel modes when individuals are presented with a novel (on-demand) mobility option. It addresses the following question: Can machine learning be applied to model individual taste heterogeneity (preference heterogeneity for travel modes and response heterogeneity to travel attributes) in travel mode choice? This paper first develops a high-accuracy classifier to predict mode-switching behavior under a hypothetical Mobility-on-Demand Transit system (i.e., stated-preference data), which represents the case study underlying this research. We show that this classifier naturally captures individual heterogeneity available in the data. Moreover, the paper derives insights on heterogeneous switching behaviors through the generation of marginal effects and elasticities by current travel mode, partial dependence plots, and individual conditional expectation plots. The paper also proposes two new model-agnostic interpretation tools for machine learning, i.e., conditional partial dependence plots and conditional individual partial dependence plots, specifically designed to examine response heterogeneity. The results on the case study show that the machine-learning classifier, together with model-agnostic interpretation tools, provides valuable insights on travel mode switching behavior for different individuals and population segments. For example, the existing drivers are more sensitive to additional pickups than people using other travel modes, and current transit users are generally willing to share rides but reluctant to take any additional transfers.

Multiple hypothesis testing, a situation when we wish to consider many hypotheses, is a core problem in statistical inference that arises in almost every scientific field. In this setting, controlling the false discovery rate (FDR), which is the expected proportion of type I error, is an important challenge for making meaningful inferences. In this paper, we consider the problem of controlling FDR in an online manner. Concretely, we consider an ordered, possibly infinite, sequence of hypotheses, arriving one at each timestep, and for each hypothesis we observe a p-value along with a set of features specific to that hypothesis. The decision whether or not to reject the current hypothesis must be made immediately at each timestep, before the next hypothesis is observed. The model of multi-dimensional feature set provides a very general way of leveraging the auxiliary information in the data which helps in maximizing the number of discoveries. We propose a new class of powerful online testing procedures, where the rejections thresholds (significance levels) are learnt sequentially by incorporating contextual information and previous results. We prove that any rule in this class controls online FDR under some standard assumptions. We then focus on a subclass of these procedures, based on weighting significance levels, to derive a practical algorithm that learns a parametric weight function in an online fashion to gain more discoveries. We also theoretically prove, in a stylized setting, that our proposed procedures would lead to an increase in the achieved statistical power over a popular online testing procedure proposed by Javanmard & Montanari (2018). Finally, we demonstrate the favorable performance of our procedure, by comparing it to state-of-the-art online multiple testing procedures, on both synthetic data and real data generated from different applications.