In many real-world applications, predictive methods are used to provide inputs for downstream optimization problems. It has been shown that using the downstream task-based objective to learn the intermediate predictive model is often better than using only intermediate task objectives, such as prediction error. The learning task in the former approach is referred to as end-to-end learning. The difficulty in end-to-end learning lies in differentiating through the optimization problem. Therefore, we propose a neural network architecture that can learn to approximately solve these optimization problems, particularly ensuring its output satisfies the feasibility constraints via alternate projections. We show these projections converge at a geometric rate to the exact projection. Our approach is more computationally efficient than existing methods as we do not need to solve the original optimization problem at each iteration. Furthermore, our approach can be applied to a wider range of optimization problems. We apply this to a shortest path problem for which the first stage forecasting problem is a computer vision task of predicting edge costs from terrain maps, a capacitated multi-product newsvendor problem, and a maximum matching problem. We show that this method out-performs existing approaches in terms of final task-based loss and training time.

Selecting the right set of hyperparameters is crucial in time series forecasting. The classical temporal cross-validation framework for hyperparameter optimization (HPO) often leads to poor test performance because of a possible mismatch between validation and test periods. To address this test-validation mismatch, we propose a novel technique, H-Pro to drive HPO via test proxies by exploiting data hierarchies often associated with time series datasets. Since higher-level aggregated time series often show less irregularity and better predictability as compared to the lowest-level time series which can be sparse and intermittent, we optimize the hyperparameters of the lowest-level base-forecaster by leveraging the proxy forecasts for the test period generated from the forecasters at higher levels. H-Pro can be applied on any off-the-shelf machine learning model to perform HPO. We validate the efficacy of our technique with extensive empirical evaluation on five publicly available hierarchical forecasting datasets. Our approach outperforms existing state-of-the-art methods in Tourism, Wiki, and Traffic datasets, and achieves competitive result in Tourism-L dataset, without any model-specific enhancements. Moreover, our method outperforms the winning method of the M5 forecast accuracy competition.

Today’s highly instrumented systems generate large amounts of time series data from many different domains. In order to create meaningful insights from these data, techniques are needed to handle the collection, processing, and analysis at scale. The high frequency and volume of data that is generated introduces several challenges including data transformation, managing concept drift, the operational cost of model re-training and tracking, and scaling hyperparameter optimization.Incremental machine learning can provide a viable solution to handle these kinds of data. Further, distributed machine learning can be an efficient technique to improve performance, increase accuracy, and scale to larger input sizes.In this paper, we introduce a framework that combines the computational capabilities of Apache Spark and the workflow parallelization of Ray for distributed incremental learning. We conduct an empirical analysis of our framework for time series forecasting using the Walmart M5 dataset. The system can perform a parameter search on streaming data with concept drift producing a robust pipeline that fits high-volume data effectively. The results are encouraging and substantiate system proficiency over traditional big data analysis approaches that exclusively use either offline or online training.

Deep generative models, such as Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs), have been employed widely in computational creativity research. However, such models discourage out-of-distribution generation to avoid spurious sample generation, thereby limiting their creativity. Thus, incorporating research on human creativity into generative deep learning techniques presents an opportunity to make their outputs more compelling and human-like. As we see the emergence of generative models directed toward creativity research, a need for machine learning-based surrogate metrics to characterize creative output from these models is imperative. We propose group-based subset scanning to identify, quantify, and characterize creative processes by detecting a subset of anomalous node-activations in the hidden layers of the generative models. Our experiments on the standard image benchmarks and their ``creatively generated'' variants reveal that the proposed subset scores distribution is more useful for detecting novelty in creative processes in the activation space rather than the pixel space. Further, we found that creative samples generate larger subsets of anomalies than normal or non-creative samples across datasets. The node activations highlighted during the creative decoding process are different from those responsible for the normal sample generation. Lastly, we assess if the images from the subsets selected by our method were also found creative by human evaluators, presenting a link between creativity perception in humans and node activations within deep neural nets.

Probabilistic forecasting of high dimensional multivariate time series is a notoriously challenging task, both in terms of computational burden and distribution modeling. Most previous work either makes simple distribution assumptions or abandons modeling cross-series correlations. A promising line of work exploits scalable matrix factorization for latent-space forecasting, but is limited to linear embeddings, unable to model distributions, and not trainable end-to-end when using deep learning forecasting. We introduce a novel temporal latent auto-encoder method which enables nonlinear factorization of multivariate time series, learned end-to-end with a temporal deep learning latent space forecast model. By imposing a probabilistic latent space model, complex distributions of the input series are modeled via the decoder. Extensive experiments demonstrate that our model achieves state-of-the-art performance on many popular multivariate datasets, with gains sometimes as high as 50% for several standard metrics.

The field of Deep Learning is rich with empirical evidence of human-like performance on a variety of prediction tasks. However, despite these successes, the recent Predicting Generalization in Deep Learning (PGDL) NeurIPS 2020 competition suggests that there is a need for more robust and efficient measures of network generalization. In this work, we propose a new framework for evaluating the generalization capabilities of trained networks. We use perturbation response (PR) curves that capture the accuracy change of a given network as a function of varying levels of training sample perturbation. From these PR curves, we derive novel statistics that capture generalization capability. Specifically, we introduce two new measures for accurately predicting generalization gaps: the Gi-score and Pal-score, which are inspired by the Gini coefficient and Palma ratio (measures of income inequality), that accurately predict generalization gaps. Using our framework applied to intra and inter-class sample mixup, we attain better predictive scores than the current state-of-the-art measures on a majority of tasks in the PGDL competition. In addition, we show that our framework and the proposed statistics can be used to capture to what extent a trained network is invariant to a given parametric input transformation, such as rotation or translation. Therefore, these generalization gap prediction statistics also provide a useful means for selecting optimal network architectures and hyperparameters that are invariant to a certain perturbation.

Creativity, a process that generates novel and meaningful ideas, involves increased association between task-positive (control) and task-negative (default) networks in the human brain. Inspired by this seminal finding, in this study we propose a creative decoder within a deep generative framework, which involves direct modulation of the neuronal activation pattern after sampling from the learned latent space. The proposed approach is fully unsupervised and can be used off- the-shelf. Several novelty metrics and human evaluation were used to evaluate the creative capacity of the deep decoder. Our experiments on different image datasets (MNIST, FMNIST, MNIST+FMNIST, WikiArt and CelebA) reveal that atypical co-activation of highly activated and weakly activated neurons in a deep decoder promotes generation of novel and meaningful artifacts.

With the rapid growth of e-tail, the cost to handle returned online orders also increases significantly and has become a major challenge in the e-commerce industry. Accurate prediction of product returns allows e-tailers to prevent problematic transactions in advance. However, the limited existing work for modeling customer online shopping behaviors and predicting their return actions fail to integrate the rich information in the product purchase and return history (e.g., return history, purchase-no-return behavior, and customer/product similarity). Furthermore, the large-scale data sets involved in this problem, typically consisting of millions of customers and tens of thousands of products, also render existing methods inefficient and ineffective at predicting the product returns. To address these problems, in this paper, we propose to use a weighted hybrid graph to represent the rich information in the product purchase and return history, in order to predict product returns. The proposed graph consists of both customer nodes and product nodes, undirected edges reflecting customer return history and customer/product similarity based on their attributes, as well as directed edges discriminating purchase-no-return and no-purchase actions. Based on this representation, we study a random-walk-based local algorithm for predicting product return propensity for each customer, whose computational complexity depends only on the size of the output cluster rather than the entire graph. Such a property makes the proposed local algorithm particularly suitable for processing the large-scale data sets to predict product returns. To test the performance of the proposed techniques, we evaluate the graph model and algorithm on multiple e-commerce data sets, showing improved performance over state-of-the-art methods.

Multi-view semi-supervised learning methods try to exploit the combination of multiple views along with large amounts of unlabeled data in order to learn better predictive functions when limited labeled data is available. However, lack of complete view data limits the applicability of multi-view semi-supervised learning to real world data. Commonly, one data view is readily and cheaply available, but additionally views may be costly or only available in some cases. This work aims to make multi-view semi-supervised learning approaches more applicable to real world data specifically by addressing the issue of missing views.

Effectively utilizing readily available auxiliary data to improve predictive performance on new modeling tasks is a key problem in data mining. In this research, the goal is to transfer knowledge between sources of data, particularly when ground-truth information for the new modeling task is scarce or is expensive to collect where leveraging any auxiliary sources of data becomes a necessity. Toward seamless knowledge transfer among tasks, effective representation of the data is a critical but yet not fully explored research area for the data engineer and data miner. Here, we present a technique based on the idea of sparse coding, which essentially attempts to find an embedding for the data by assigning feature values based on subspace cluster membership. We modify the idea of sparse coding by focusing the identification of shared clusters between data when source and target data may have different distributions. In our paper, we point out cases where a direct application of sparse coding will lead to a failure of knowledge transfer. We then present the details of our extension to sparse coding, by incorporating distribution distance estimates for the embedded data, and show that the proposed algorithm can overcome the shortcomings of the sparse coding algorithm on synthetic data and achieve improved predictive performance on a real world chemical toxicity transfer learning task.

Effectively utilizing readily available auxiliary data to improve predictive performance on new modeling tasks is a key problem in data mining. In this research the goal is to transfer knowledge between sources of data, particularly when ground truth information for the new modeling task is scarce or is expensive to collect where leveraging any auxiliary sources of data becomes a necessity. Towards seamless knowledge transfer among tasks, effective representation of the data is a critical but yet not fully explored research area for the data engineer and data miner. Here we present a technique based on the idea of sparse coding, which essentially attempts to find an embedding for the data by assigning feature values based on subspace cluster membership. We modify the idea of sparse coding by focusing the identification of shared clusters between data when source and target data may have different distributions. In our paper, we point out cases where a direct application of sparse coding will lead to a failure of knowledge transfer. We then present the details of our extension to sparse coding, by incorporating distribution distance estimates for the embedded data, and show that the proposed algorithm can overcome the shortcomings of the sparse coding algorithm on synthetic data and achieve improved predictive performance on a real world chemical toxicity transfer learning task.

In the standard formalization of supervised learning problems, a datum is represented as a vector of features without prior knowledge about relationships among features. However, for many real world problems, we have such prior knowledge about structure relationships among features. For instance, in Microarray analysis where the genes are features, the genes form biological pathways. Such prior knowledge should be incorporated to build a more accurate and interpretable model, especially in applications with high dimensionality and low sample sizes. Towards an efficient incorporation of the structure relationships, we have designed a classification model where we use an undirected graph to capture the relationship of features. In our method, we combine both L1 norm and Laplacian based L2 norm regularization with logistic regression. In this approach, we enforce model sparsity and smoothness among features to identify a small subset of grouped features. We have derived efficient optimization algorithms based on coordinate decent for the new formulation. Using comprehensive experimental study, we have demonstrated the effectiveness of the proposed learning methods.

Recently there has been increasing interest in the problem of transfer learning, in which the typical assumption that training and testing data are drawn from identical distributions is relaxed. We specifically address the problem of transductive transfer learning in which we have access to labeled training data and unlabeled testing data potentially drawn from different, yet related distributions, and the goal is to leverage the labeled training data to learn a classifier to correctly predict data from the testing distribution.

There has been increasing interest in incorporating sensing systems into objects or the environment for monitoring purposes. In this work we compare approaches to performing fully-distributed anomaly detection as a means of detecting security threats for objects equipped with sensing and communication abilities. With the desirability of increased visibility into the cargo in the transport chain and the goal of improving security, we consider the approach of equipping cargo with sensing and communication capabilities as a means of ensuring the security of the cargo as a key application. We have gathered real sensor test data from a rail trial and used the collected data to test the feasibility of the anomaly detection approach. The results demonstrate the effectiveness of our approach.

Data with intrinsic feature relationships are becoming abundant in many applications including bioinformatics and sensor network analysis. In this paper we consider a classification problem where there is a fixed and known binary relation defined on the features of a set of multivariate random variables. We formalize such a problem as an aligned graph classification problem. By incorporating this feature relationship in the learning process we aim to obtain improved classification performance over conventional learning that does not consider the additional information of the feature relationship. To incorporate the feature relationship, we extend logistic regression and use a regularization term that includes the normalized Laplacian of the graph, similar to the L2 regularization, deriving a modified optimization problem and solution. We demonstrate the effectiveness of our method and compare it to other methods using simulated and real data sets.