xGEM
This work proposes xGEMs or manifold guided exemplars, a framework to understand black-box classifier behavior by exploring the landscape of the underlying data manifold as data points cross decision boundaries. To do so, we train an unsupervised implicit generative model — treated as a proxy to the data manifold. We summarize black-box model behavior quantitatively by perturbing data samples along the manifold. We demonstrate xGEMs’ ability to detect and quantify bias in model learning and also for understanding the changes in model behavior as training progresses. …

TamperNN
Neural networks are powering the deployment of embedded devices and Internet of Things. Applications range from personal assistants to critical ones such as self-driving cars. It has been shown recently that models obtained from neural nets can be trojaned ; an attacker can then trigger an arbitrary model behavior facing crafted inputs. This has a critical impact on the security and reliability of those deployed devices. We introduce novel algorithms to detect the tampering with deployed models, classifiers in particular. In the remote interaction setup we consider, the proposed strategy is to identify markers of the model input space that are likely to change class if the model is attacked, allowing a user to detect a possible tampering. This setup makes our proposal compatible with a wide rage of scenarios, such as embedded models, or models exposed through prediction APIs. We experiment those tampering detection algorithms on the canonical MNIST dataset, over three different types of neural nets, and facing five different attacks (trojaning, quantization, fine-tuning, compression and watermarking). We then validate over five large models (VGG16, VGG19, ResNet, MobileNet, DenseNet) with a state of the art dataset (VGGFace2), and report results demonstrating the possibility of an efficient detection of model tampering. …

Agent-Based Model (ABM)
An agent-based model (ABM) is a class of computational models for simulating the actions and interactions of autonomous agents (both individual or collective entities such as organizations or groups) with a view to assessing their effects on the system as a whole. It combines elements of game theory, complex systems, emergence, computational sociology, multi-agent systems, and evolutionary programming. Monte Carlo methods are used to introduce randomness. Particularly within ecology, ABMs are also called individual-based models (IBMs), and individuals within IBMs may be simpler than fully autonomous agents within ABMs. A review of recent literature on individual-based models, agent-based models, and multiagent systems shows that ABMs are used on non-computing related scientific domains including biology, ecology and social science. Agent-based modeling is related to, but distinct from, the concept of multi-agent systems or multi-agent simulation in that the goal of ABM is to search for explanatory insight into the collective behavior of agents obeying simple rules, typically in natural systems, rather than in designing agents or solving specific practical or engineering problems. Agent-based models are a kind of microscale model that simulate the simultaneous operations and interactions of multiple agents in an attempt to re-create and predict the appearance of complex phenomena. The process is one of emergence from the lower (micro) level of systems to a higher (macro) level. As such, a key notion is that simple behavioral rules generate complex behavior. This principle, known as K.I.S.S. (‘Keep it simple, stupid’), is extensively adopted in the modeling community. Another central tenet is that the whole is greater than the sum of the parts. Individual agents are typically characterized as boundedly rational, presumed to be acting in what they perceive as their own interests, such as reproduction, economic benefit, or social status, using heuristics or simple decision-making rules. ABM agents may experience ‘learning’, adaptation, and reproduction. Most agent-based models are composed of: (1) numerous agents specified at various scales (typically referred to as agent-granularity); (2) decision-making heuristics; (3) learning rules or adaptive processes; (4) an interaction topology; and (5) an environment. ABMs are typically implemented as computer simulations, either as custom software, or via ABM toolkits, and this software can be then used to test how changes in individual behaviors will affect the system’s emerging overall behavior. …

Deep Polynomial Network (DPN)
The cloud-based speech recognition/API provides developers or enterprises an easy way to create speech-enabled features in their applications. However, sending audios about personal or company internal information to the cloud, raises concerns about the privacy and security issues. The recognition results generated in cloud may also reveal some sensitive information. This paper proposes a deep polynomial network (DPN) that can be applied to the encrypted speech as an acoustic model. It allows clients to send their data in an encrypted form to the cloud to ensure that their data remains confidential, at mean while the DPN can still make frame-level predictions over the encrypted speech and return them in encrypted form. One good property of the DPN is that it can be trained on unencrypted speech features in the traditional way. To keep the cloud away from the raw audio and recognition results, a cloud-local joint decoding framework is also proposed. We demonstrate the effectiveness of model and framework on the Switchboard and Cortana voice assistant tasks with small performance degradation and latency increased comparing with the traditional cloud-based DNNs. …

LeanResNet
Convolutional Neural Networks (CNNs) filter the input data using a series of spatial convolution operators with compact stencils and point-wise non-linearities. Commonly, the convolution operators couple features from all channels, which leads to immense computational cost in the training of and prediction with CNNs. To improve the efficiency of CNNs, we introduce lean convolution operators that reduce the number of parameters and computational complexity. Our new operators can be used in a wide range of existing CNNs. Here, we exemplify their use in residual networks (ResNets), which have been very reliable for a few years now and analyzed intensively. In our experiments on three image classification problems, the proposed LeanResNet yields results that are comparable to other recently proposed reduced architectures using similar number of parameters. …

Half-Life of Data
Radioactive substances have a half life. The half life is the amount of time it takes for the substance to lose half of its radioactivity. Half life is used more generally in physics as a way to estimate the rate of decay. We can apply exactly the same principle – the rate of decay – to business information. Like natural materials, data is subject to deterioration over time. In science, the half life of a given substance could be milliseconds. It could be many thousands of years. The half life of data has been measured, and it may be shorter than you were expecting.
http://…/infographics-the-half-life-of-data …

Variational Inference
One of the core problems of modern statistics is to approximate difficult-to-compute probability densities. This problem is especially important in Bayesian statistics, which frames all inference about unknown quantities as a calculation involving the posterior density. In this paper, we review variational inference (VI), a method from machine learning that approximates probability densities through optimization. VI has been used in many applications and tends to be faster than classical methods, such as Markov chain Monte Carlo sampling. The idea behind VI is to first posit a family of densities and then to find the member of that family which is close to the target. Closeness is measured by Kullback-Leibler divergence. We review the ideas behind mean-field variational inference, discuss the special case of VI applied to exponential family models, present a full example with a Bayesian mixture of Gaussians, and derive a variant that uses stochastic optimization to scale up to massive data. We discuss modern research in VI and highlight important open problems. VI is powerful, but it is not yet well understood. Our hope in writing this paper is to catalyze statistical research on this class of algorithms.
Fast yet Simple Natural-Gradient Descent for Variational Inference in Complex Models …

Event2Vec
Network representation learning (NRL) has been widely used to help analyze large-scale networks through mapping original networks into a low-dimensional vector space. However, existing NRL methods ignore the impact of properties of relations on the object relevance in heterogeneous information networks (HINs). To tackle this issue, this paper proposes a new NRL framework, called Event2vec, for HINs to consider both quantities and properties of relations during the representation learning process. Specifically, an event (i.e., a complete semantic unit) is used to represent the relation among multiple objects, and both event-driven first-order and second-order proximities are defined to measure the object relevance according to the quantities and properties of relations. We theoretically prove how event-driven proximities can be preserved in the embedding space by Event2vec, which utilizes event embeddings to facilitate learning the object embeddings. Experimental studies demonstrate the advantages of Event2vec over state-of-the-art algorithms on four real-world datasets and three network analysis tasks (including network reconstruction, link prediction, and node classification). …

Deep Octonion Network
Deep learning is a research hot topic in the field of machine learning. Real-value neural networks (Real NNs), especially deep real networks (DRNs), have been widely used in many research fields. In recent years, the deep complex networks (DCNs) and the deep quaternion networks (DQNs) have attracted more and more attentions. The octonion algebra, which is an extension of complex algebra and quaternion algebra, can provide more efficient and compact expression. This paper constructs a general framework of deep octonion networks (DONs) and provides the main building blocks of DONs such as octonion convolution, octonion batch normalization and octonion weight initialization; DONs are then used in image classification tasks for CIFAR-10 and CIFAR-100 data sets. Compared with the DRNs, the DCNs, and the DQNs, the proposed DONs have better convergence and higher classification accuracy. The success of DONs is also explained by multi-task learning. …

AutoML for Loss Function Search (AM-LFS)
Designing an effective loss function plays an important role in visual analysis. Most existing loss function designs rely on hand-crafted heuristics that require domain experts to explore the large design space, which is usually sub-optimal and time-consuming. In this paper, we propose AutoML for Loss Function Search (AM-LFS) which leverages REINFORCE to search loss functions during the training process. The key contribution of this work is the design of search space which can guarantee the generalization and transferability on different vision tasks by including a bunch of existing prevailing loss functions in a unified formulation. We also propose an efficient optimization framework which can dynamically optimize the parameters of loss function’s distribution during training. Extensive experimental results on four benchmark datasets show that, without any tricks, our method outperforms existing hand-crafted loss functions in various computer vision tasks. …

Model-Based Task Transfer Learning (MBTTL)
A model-based task transfer learning (MBTTL) method is presented. We consider a constrained nonlinear dynamical system and assume that a dataset of state and input pairs that solve a task T1 is available. Our objective is to find a feasible state-feedback policy for a second task, T1, by using stored data from T2. Our approach applies to tasks T2 which are composed of the same subtasks as T1, but in different order. In this paper we formally introduce the definition of subtask, the MBTTL problem and provide examples of MBTTL in the fields of autonomous cars and manipulators. Then, a computationally efficient approach to solve the MBTTL problem is presented along with proofs of feasibility for constrained linear dynamical systems. Simulation results show the effectiveness of the proposed method. …

Collaborative Distribution Alignment (CDA)
In conventional domain adaptation, a critical assumption is that there exists a fully labeled domain (source) that contains the same label space as another unlabeled or scarcely labeled domain (target). However, in the real world, there often exist application scenarios in which both domains are partially labeled and not all classes are shared between these two domains. Thus, it is meaningful to let partially labeled domains learn from each other to classify all the unlabeled samples in each domain under an open-set setting. We consider this problem as weakly supervised open-set domain adaptation. To address this practical setting, we propose the Collaborative Distribution Alignment (CDA) method, which performs knowledge transfer bilaterally and works collaboratively to classify unlabeled data and identify outlier samples. Extensive experiments on the Office benchmark and an application on person reidentification show that our method achieves state-of-the-art performance. …

Batched Successive Elimination (BaSE)
In this paper, we study the multi-armed bandit problem in the batched setting where the employed policy must split data into a small number of batches. While the minimax regret for the two-armed stochastic bandits has been completely characterized in \cite{perchet2016batched}, the effect of the number of arms on the regret for the multi-armed case is still open. Moreover, the question whether adaptively chosen batch sizes will help to reduce the regret also remains underexplored. In this paper, we propose the BaSE (batched successive elimination) policy to achieve the rate-optimal regret (within logarithmic factors) for batched multi-armed bandits, with matching lower bounds even if the batch sizes are determined in a data-driven manner. …

Deep Adversarial Social Recommendation (DASO)
Recent years have witnessed rapid developments on social recommendation techniques for improving the performance of recommender systems due to the growing influence of social networks to our daily life. The majority of existing social recommendation methods unify user representation for the user-item interactions (item domain) and user-user connections (social domain). However, it may restrain user representation learning in each respective domain, since users behave and interact differently in the two domains, which makes their representations to be heterogeneous. In addition, most of traditional recommender systems can not efficiently optimize these objectives, since they utilize negative sampling technique which is unable to provide enough informative guidance towards the training during the optimization process. In this paper, to address the aforementioned challenges, we propose a novel deep adversarial social recommendation framework DASO. It adopts a bidirectional mapping method to transfer users’ information between social domain and item domain using adversarial learning. Comprehensive experiments on two real-world datasets show the effectiveness of the proposed framework. …

Latent Entity Typing (LET)
Classifying semantic relations between entity pairs in sentences is an important task in Natural Language Processing (NLP). Most previous models for relation classification rely on the high-level lexical and syntactic features obtained by NLP tools such as WordNet, dependency parser, part-of-speech (POS) tagger, and named entity recognizers (NER). In addition, state-of-the-art neural models based on attention mechanisms do not fully utilize information of entity that may be the most crucial features for relation classification. To address these issues, we propose a novel end-to-end recurrent neural model which incorporates an entity-aware attention mechanism with a latent entity typing (LET) method. Our model not only utilizes entities and their latent types as features effectively but also is more interpretable by visualizing attention mechanisms applied to our model and results of LET. Experimental results on the SemEval-2010 Task 8, one of the most popular relation classification task, demonstrate that our model outperforms existing state-of-the-art models without any high-level features. …

NATTACK
Powerful adversarial attack methods are vital for understanding how to construct robust deep neural networks (DNNs) and for thoroughly testing defense techniques. In this paper, we propose a black-box adversarial attack algorithm that can defeat both vanilla DNNs and those generated by various defense techniques developed recently. Instead of searching for an ‘optimal’ adversarial example for a benign input to a targeted DNN, our algorithm finds a probability density distribution over a small region centered around the input, such that a sample drawn from this distribution is likely an adversarial example, without the need of accessing the DNN’s internal layers or weights. Our approach is universal as it can successfully attack different neural networks by a single algorithm. It is also strong; according to the testing against 2 vanilla DNNs and 13 defended ones, it outperforms state-of-the-art black-box or white-box attack methods for most test cases. Additionally, our results reveal that adversarial training remains one of the best defense techniques, and the adversarial examples are not as transferable across defended DNNs as them across vanilla DNNs. …

Self-Adjusting Linear Network
Emerging networked systems become increasingly flexible and reconfigurable. This introduces an opportunity to adjust networked systems in a demand-aware manner, leveraging spatial and temporal locality in the workload for online optimizations. However, it also introduces a trade-off: while more frequent adjustments can improve performance, they also entail higher reconfiguration costs. This paper initiates the formal study of linear networks which self-adjust to the demand in an online manner, striking a balance between the benefits and costs of reconfigurations. We show that the underlying algorithmic problem can be seen as a distributed generalization of the classic dynamic list update problem known from self-adjusting datastructures: in a network, requests can occur between node pairs. This distributed version turns out to be significantly harder than the classical problem in generalizes. Our main results are a $\Omega(\log{n})$ lower bound on the competitive ratio, and a (distributed) online algorithm that is $O(\log{n})$-competitive if the communication requests are issued according to a linear order. …

Youden’s J Statistic
Youden’s J statistic (also called Youden’s index) is a single statistic that captures the performance of a diagnostic test. …

Generalized Approximate Survey Propagation (GASP)
In Generalized Linear Estimation (GLE) problems, we seek to estimate a signal that is observed through a linear transform followed by a component-wise, possibly nonlinear and noisy, channel. In the Bayesian optimal setting, Generalized Approximate Message Passing (GAMP) is known to achieve optimal performance for GLE. However, its performance can significantly degrade whenever there is a mismatch between the assumed and the true generative model, a situation frequently encountered in practice. In this paper, we propose a new algorithm, named Generalized Approximate Survey Propagation (GASP), for solving GLE in the presence of prior or model mis-specifications. As a prototypical example, we consider the phase retrieval problem, where we show that GASP outperforms the corresponding GAMP, reducing the reconstruction threshold and, for certain choices of its parameters, approaching Bayesian optimal performance. Furthermore, we present a set of State Evolution equations that exactly characterize the dynamics of GASP in the high-dimensional limit. …

Random Geometric Graph (RGG)
We propose an interdependent random geometric graph (RGG) model for interdependent networks. Based on this model, we study the robustness of two interdependent spatially embedded networks where interdependence exists between geographically nearby nodes in the two networks. We study the emergence of the giant mutual component in two interdependent RGGs as node densities increase, and define the percolation threshold as a pair of node densities above which the giant mutual component first appears. In contrast to the case for a single RGG, where the percolation threshold is a unique scalar for a given connection distance, for two interdependent RGGs, multiple pairs of percolation thresholds may exist, given that a smaller node density in one RGG may increase the minimum node density in the other RGG in order for a giant mutual component to exist. We derive analytical upper bounds on the percolation thresholds of two interdependent RGGs by discretization, and obtain $99\%$ confidence intervals for the percolation thresholds by simulation. Based on these results, we derive conditions for the interdependent RGGs to be robust under random failures and geographical attacks. …

Trace Lasso-L1 Graph Cut (TL-L1GC)
This work proposes an adaptive trace lasso regularized L1-norm based graph cut method for dimensionality reduction of Hyperspectral images, called as `Trace Lasso-L1 Graph Cut’ (TL-L1GC). The underlying idea of this method is to generate the optimal projection matrix by considering both the sparsity as well as the correlation of the data samples. The conventional L2-norm used in the objective function is sensitive to noise and outliers. Therefore, in this work L1-norm is utilized as a robust alternative to L2-norm. Besides, for further improvement of the results, we use a penalty function of trace lasso with the L1GC method. It adaptively balances the L2-norm and L1-norm simultaneously by considering the data correlation along with the sparsity. We obtain the optimal projection matrix by maximizing the ratio of between-class dispersion to within-class dispersion using L1-norm with trace lasso as the penalty. Furthermore, an iterative procedure for this TL-L1GC method is proposed to solve the optimization function. The effectiveness of this proposed method is evaluated on two benchmark HSI datasets. …

PaintBot
We propose a new automated digital painting framework, based on a painting agent trained through reinforcement learning. To synthesize an image, the agent selects a sequence of continuous-valued actions representing primitive painting strokes, which are accumulated on a digital canvas. Action selection is guided by a given reference image, which the agent attempts to replicate subject to the limitations of the action space and the agent’s learned policy. The painting agent policy is determined using a variant of proximal policy optimization reinforcement learning. During training, our agent is presented with patches sampled from an ensemble of reference images. To accelerate training convergence, we adopt a curriculum learning strategy, whereby reference patches are sampled according to how challenging they are using the current policy. We experiment with differing loss functions, including pixel-wise and perceptual loss, which have consequent differing effects on the learned policy. We demonstrate that our painting agent can learn an effective policy with a high dimensional continuous action space comprising pen pressure, width, tilt, and color, for a variety of painting styles. Through a coarse-to-fine refinement process our agent can paint arbitrarily complex images in the desired style. …

Dynamic Principal Component Analysis
In areas of application, including actuarial science and demography, it is increasingly common to consider a time series of curves; an example of this is age-specific mortality rates observed over a period of years. Given that age can be treated as a discrete or continuous variable, a dimension reduction technique, such as principal component analysis, is often implemented. However, in the presence of moderate to strong temporal dependence, static principal component analysis commonly used for analyzing independent and identically distributed data may not be adequate. As an alternative, we consider a \textit{dynamic} principal component approach to model temporal dependence in a time series of curves. Inspired by Brillinger’s (1974) theory of dynamic principal components, we introduce a dynamic principal component analysis, which is based on eigen-decomposition of estimated long-run covariance. Through a series of empirical applications, we demonstrate the potential improvement of one-year-ahead point and interval forecast accuracies that the dynamic principal component regression entails when compared with the static counterpart. …

Segmentation-Based Matrix Factorization (SPMF)
The traditional social recommendation algorithm ignores the following fact: the preferences of users with trust relationships are not necessarily similar, and the consideration of user preference similarity should be limited to specific areas. A social trust and preference segmentation-based matrix factorization (SPMF) recommendation system is proposed to solve the above-mentioned problems. Experimental results based on the Ciao and Epinions datasets show that the accuracy of the SPMF algorithm is significantly higher than that of some state-of-the-art recommendation algorithms. The proposed SPMF algorithm is a more accurate and effective recommendation algorithm based on distinguishing the difference of trust relations and preference domain, which can support commercial activities such as product marketing. …

Class-Agnostic Segmentation Network (CANet)
Recent progress in semantic segmentation is driven by deep Convolutional Neural Networks and large-scale labeled image datasets. However, data labeling for pixel-wise segmentation is tedious and costly. Moreover, a trained model can only make predictions within a set of pre-defined classes. In this paper, we present CANet, a class-agnostic segmentation network that performs few-shot segmentation on new classes with only a few annotated images available. Our network consists of a two-branch dense comparison module which performs multi-level feature comparison between the support image and the query image, and an iterative optimization module which iteratively refines the predicted results. Furthermore, we introduce an attention mechanism to effectively fuse information from multiple support examples under the setting of k-shot learning. Experiments on PASCAL VOC 2012 show that our method achieves a mean Intersection-over-Union score of 55.4% for 1-shot segmentation and 57.1% for 5-shot segmentation, outperforming state-of-the-art methods by a large margin of 14.6% and 13.2%, respectively. …

Multi-Parameter Regression (MPR)
It is standard practice for covariates to enter a parametric model through a single distributional parameter of interest, for example, the scale parameter in many standard survival models. Indeed, the well-known proportional hazards model is of this kind. In this paper we discuss a more general approach whereby covariates enter the model through more than one distributional parameter simultaneously (e.g., scale and shape parameters). We refer to this practice as ‘multi-parameter regression’ (MPR) modelling and explore its use in a survival analysis context. We find that multi-parameter regression leads to more flexible models which can offer greater insight into the underlying data generating process. To illustrate the concept, we consider the two-parameter Weibull model which leads to time-dependent hazard ratios, thus relaxing the typical proportional hazards assumption and motivating a new test of proportionality. A novel variable selection strategy is introduced for such multi-parameter regression models. It accounts for the correlation arising between the estimated regression coefficients in two or more linear predictors – a feature which has not been considered by other authors in similar settings. The methods discussed have been implemented in the mpr package in R. …

Deep Neural Network Ensemble
Current deep neural networks suffer from two problems; first, they are hard to interpret, and second, they suffer from overfitting. There have been many attempts to define interpretability in neural networks, but they typically lack causality or generality. A myriad of regularization techniques have been developed to prevent overfitting, and this has driven deep learning to become the hot topic it is today; however, while most regularization techniques are justified empirically and even intuitively, there is not much underlying theory. This paper argues that to extract the features used in neural networks to make decisions, it’s important to look at the paths between clusters existing in the hidden spaces of neural networks. These features are of particular interest because they reflect the true decision making process of the neural network. This analysis is then furthered to present an ensemble algorithm for arbitrary neural networks which has guarantees for test accuracy. Finally, a discussion detailing the aforementioned guarantees is introduced and the implications to neural networks, including an intuitive explanation for all current regularization methods, are presented. The ensemble algorithm has generated state-of-the-art results for Wide-ResNet on CIFAR-10 and has improved test accuracy for all models it has been applied to. …

Tensor Train PCA (TT-PCA)
Tensor train is a hierarchical tensor network structure that helps alleviate the curse of dimensionality by parameterizing large-scale multidimensional data via a set of network of low-rank tensors. Associated with such a construction is a notion of Tensor Train subspace and in this paper we propose a TT-PCA algorithm for estimating this structured subspace from the given data. By maintaining low rank tensor structure, TT-PCA is more robust to noise comparing with PCA or Tucker-PCA. This is borne out numerically by testing the proposed approach on the Extended YaleFace Dataset B. …

G-Rap
Finding the best neural network configuration for a given goal can be challenging, especially when it is not possible to assess the output quality of a network automatically. We present G-Rap, an interactive interface based on Visual Analytics principles for comparing outputs of multiple RNNs for the same training data. G-Rap enables an iterative result generation process that allows a user to evaluate the outputs with contextual statistics. …

Relational Induction Neural Network (RINN)
The automation design of microwave integrated circuits (MWIC) has long been viewed as a fundamental challenge for artificial intelligence owing to its larger solution space and structural complexity than Go. Here, we developed a novel artificial agent, termed Relational Induction Neural Network, that can lead to an automotive design of MWIC and avoid brute-force computing to examine every possible solution, which is a significant breakthrough in the field of electronics. Through the experiments on microwave transmission line circuit, filter circuit and antenna circuit design tasks, strongly competitive results are obtained respectively. Compared with the traditional reinforcement learning method, the learning curve shows that the proposed architecture is able to quickly converge to the pre-designed MWIC model and the convergence rate is up to four orders of magnitude. This is the first study which has been shown that an agent through training or learning to automatically induct the relationship between MWIC’s structures without incorporating any of the additional prior knowledge. Notably, the relationship can be explained in terms of the MWIC theory and electromagnetic field distribution. Our work bridges the divide between artificial intelligence and MWIC and can extend to mechanical wave, mechanics and other related fields. …

Agent-Based Computational Economics (ACE)
Agent-based computational economics (ACE) is the area of computational economics that studies economic processes, including whole economies, as dynamic systems of interacting agents. As such, it falls in the paradigm of complex adaptive systems. In corresponding agent-based models, the ‘agents’ are ‘computational objects modeled as interacting according to rules’ over space and time, not real people. The rules are formulated to model behavior and social interactions based on incentives and information. Such rules could also be the result of optimization, realized through use of AI methods (such as Q-learning and other reinforcement learning techniques). The theoretical assumption of mathematical optimization by agents in equilibrium is replaced by the less restrictive postulate of agents with bounded rationality adapting to market forces. ACE models apply numerical methods of analysis to computer-based simulations of complex dynamic problems for which more conventional methods, such as theorem formulation, may not find ready use. Starting from initial conditions specified by the modeler, the computational economy evolves over time as its constituent agents repeatedly interact with each other, including learning from interactions. In these respects, ACE has been characterized as a bottom-up culture-dish approach to the study of economic systems. ACE has a similarity to, and overlap with, game theory as an agent-based method for modeling social interactions. But practitioners have also noted differences from standard methods, for example in ACE events modeled being driven solely by initial conditions, whether or not equilibria exist or are computationally tractable, and in the modeling facilitation of agent autonomy and learning. The method has benefited from continuing improvements in modeling techniques of computer science and increased computer capabilities. The ultimate scientific objective of the method is to ‘test theoretical findings against real-world data in ways that permit empirically supported theories to cumulate over time, with each researcher’s work building appropriately on the work that has gone before.’ The subject has been applied to research areas like asset pricing, competition and collaboration, transaction costs, market structure and industrial organization and dynamics, welfare economics, and mechanism design, information and uncertainty, macroeconomics, and Marxist economics.
…

Neurally Directed Program Search (NDPS)
We study the problem of generating interpretable and verifiable policies through reinforcement learning. Unlike the popular Deep Reinforcement Learning (DRL) paradigm, in which the policy is represented by a neural network, the aim in Programmatically Interpretable Reinforcement Learning is to find a policy that can be represented in a high-level programming language. Such programmatic policies have the benefits of being more easily interpreted than neural networks, and being amenable to verification by symbolic methods. We propose a new method, called Neurally Directed Program Search (NDPS), for solving the challenging nonsmooth optimization problem of finding a programmatic policy with maxima reward. NDPS works by first learning a neural policy network using DRL, and then performing a local search over programmatic policies that seeks to minimize a distance from this neural ‘oracle’. We evaluate NDPS on the task of learning to drive a simulated car in the TORCS car-racing environment. We demonstrate that NDPS is able to discover human-readable policies that pass some significant performance bars. We also find that a well-designed policy language can serve as a regularizer, and result in the discovery of policies that lead to smoother trajectories and are more easily transferred to environments not encountered during training. …

Adaptive SVM+
Incorporating additional knowledge in the learning process can be beneficial for several computer vision and machine learning tasks. Whether privileged information originates from a source domain that is adapted to a target domain, or as additional features available at training time only, using such privileged (i.e., auxiliary) information is of high importance as it improves the recognition performance and generalization. However, both primary and privileged information are rarely derived from the same distribution, which poses an additional challenge to the recognition task. To address these challenges, we present a novel learning paradigm that leverages privileged information in a domain adaptation setup to perform visual recognition tasks. The proposed framework, named Adaptive SVM+, combines the advantages of both the learning using privileged information (LUPI) paradigm and the domain adaptation framework, which are naturally embedded in the objective function of a regular SVM. We demonstrate the effectiveness of our approach on the publicly available Animals with Attributes and INTERACT datasets and report state-of-the-art results in both of them. …

Graph Adversarial Training (GAT)
Recent efforts show that neural networks are vulnerable to small but intentional perturbations on input features in visual classification tasks. Due to the additional consideration of connections between examples (e.g., articles with citation link tend to be in the same class), graph neural networks could be more sensitive to the perturbations, since the perturbations from connected examples exacerbate the impact on a target example. Adversarial Training (AT), a dynamic regularization technique, can resist the worst-case perturbations on input features and is a promising choice to improve model robustness and generalization. However, existing AT methods focus on standard classification, being less effective when training models on graph since it does not model the impact from connected examples. In this work, we explore adversarial training on graph, aiming to improve the robustness and generalization of models learned on graph. We propose Graph Adversarial Training (GAT), which takes the impact from connected examples into account when learning to construct and resist perturbations. We give a general formulation of GAT, which can be seen as a dynamic regularization scheme based on the graph structure. To demonstrate the utility of GAT, we employ it on a state-of-the-art graph neural network model — Graph Convolutional Network (GCN). We conduct experiments on two citation graphs (Citeseer and Cora) and a knowledge graph (NELL), verifying the effectiveness of GAT which outperforms normal training on GCN by 4.51% in node classification accuracy. Codes will be released upon acceptance. …

Buffered Stochastic Variational Inference (BSVI)
The recognition network in deep latent variable models such as variational autoencoders (VAEs) relies on amortized inference for efficient posterior approximation that can scale up to large datasets. However, this technique has also been demonstrated to select suboptimal variational parameters, often resulting in considerable additional error called the amortization gap. To close the amortization gap and improve the training of the generative model, recent works have introduced an additional refinement step that applies stochastic variational inference (SVI) to improve upon the variational parameters returned by the amortized inference model. In this paper, we propose the Buffered Stochastic Variational Inference (BSVI), a new refinement procedure that makes use of SVI’s sequence of intermediate variational proposal distributions and their corresponding importance weights to construct a new generalized importance-weighted lower bound. We demonstrate empirically that training the variational autoencoders with BSVI consistently out-performs SVI, yielding an improved training procedure for VAEs. …

Runtime Neuron Activation Pattern Monitoring
For using neural networks in safety critical domains, it is important to know if a decision made by a neural network is supported by prior similarities in training. We propose runtime neuron activation pattern monitoring – after the standard training process, one creates a monitor by feeding the training data to the network again in order to store the neuron activation patterns in abstract form. In operation, a classification decision over an input is further supplemented by examining if a pattern similar (measured by Hamming distance) to the generated pattern is contained in the monitor. If the monitor does not contain any pattern similar to the generated pattern, it raises a warning that the decision is not based on the training data. Our experiments show that, by adjusting the similarity-threshold for activation patterns, the monitors can report a significant portion of misclassfications to be not supported by training with a small false-positive rate, when evaluated on a test set. …

GP-MaL
Exploratory data analysis is a fundamental aspect of knowledge discovery that aims to find the main characteristics of a dataset. Dimensionality reduction, such as manifold learning, is often used to reduce the number of features in a dataset to a manageable level for human interpretation. Despite this, most manifold learning techniques do not explain anything about the original features nor the true characteristics of a dataset. In this paper, we propose a genetic programming approach to manifold learning called GP-MaL which evolves functional mappings from a high-dimensional space to a lower dimensional space through the use of interpretable trees. We show that GP-MaL is competitive with existing manifold learning algorithms, while producing models that can be interpreted and re-used on unseen data. A number of promising future directions of research are found in the process. …

BioWorkbench
Advances in sequencing techniques have led to exponential growth in biological data, demanding the development of large-scale bioinformatics experiments. Because these experiments are computation- and data-intensive, they require high-performance computing (HPC) techniques and can benefit from specialized technologies such as Scientific Workflow Management Systems (SWfMS) and databases. In this work, we present BioWorkbench, a framework for managing and analyzing bioinformatics experiments. This framework automatically collects provenance data, including both performance data from workflow execution and data from the scientific domain of the workflow application. Provenance data can be analyzed through a web application that abstracts a set of queries to the provenance database, simplifying access to provenance information. We evaluate BioWorkbench using three case studies: SwiftPhylo, a phylogenetic tree assembly workflow; SwiftGECKO, a comparative genomics workflow; and RASflow, a RASopathy analysis workflow. We analyze each workflow from both computational and scientific domain perspectives, by using queries to a provenance and annotation database. Some of these queries are available as a pre-built feature of the BioWorkbench web application. Through the provenance data, we show that the framework is scalable and achieves high-performance, reducing up to 98% of the case studies execution time. We also show how the application of machine learning techniques can enrich the analysis process. …

Dictionary Learning (DL)
Dictionary learning is a branch of signal processing and machine learning that aims at finding a frame (called dictionary) in which some training data admits a sparse representation. The sparser the representation, the better the dictionary.
Dictionary Learning Algorithms for Sparse Representation
Dictionary Learning …

Regularized Greedy Forest (RGF)
Regularized Greedy Forest wrapper of the ‘Regularized Greedy Forest’ <https://…/rgf_python> ‘python’ package, which also includes a Multi-core implementation (FastRGF) <https://…/fast_rgf>. …