Myelin
Machine learning models benefit from large and diverse datasets. Using such datasets, however, often requires trusting a centralized data aggregator. For sensitive applications like healthcare and finance this is undesirable as it could compromise patient privacy or divulge trade secrets. Recent advances in secure and privacy-preserving computation, including trusted hardware enclaves and differential privacy, offer a way for mutually distrusting parties to efficiently train a machine learning model without revealing the training data. In this work, we introduce Myelin, a deep learning framework which combines these privacy-preservation primitives, and use it to establish a baseline level of performance for fully private machine learning. …

Superhighway Construction
Cross-domain collaborative filtering (CF) aims to alleviate data sparsity in single-domain CF by leveraging knowledge transferred from related domains. Many traditional methods focus on enriching compared neighborhood relations in CF directly to address the sparsity problem. In this paper, we propose superhighway construction, an alternative explicit relation-enrichment procedure, to improve recommendations by enhancing cross-domain connectivity. Specifically, assuming partially overlapped items (users), superhighway bypasses multi-hop inter-domain paths between cross-domain users (items, respectively) with direct paths to enrich the cross-domain connectivity. The experiments conducted on a real-world cross-region music dataset and a cross-platform movie dataset show that the proposed superhighway construction significantly improves recommendation performance in both target and source domains. …

Wavenilm
Non-intrusive load monitoring (NILM) helps meet energy conservation goals by estimating individual appliance power usage from a single aggregate measurement. Deep neural networks have become increasingly popular in attempting to solve NILM problems; however, many of them are not causal which is important for real-time application. We present a causal 1-D convolutional neural network inspired by WaveNet for NILM on low-frequency data. We also study using various components of the complex power signal for NILM, and demonstrate that using all four components available in a popular NILM dataset (current, active power, reactive power, and apparent power) we achieve faster convergence and higher performance than state-of-the-art results for the same dataset. …

Distributed Expectation-Maximization (DEM)
The family of Expectation-Maximization (EM) algorithms provides a general approach to fitting flexible models for large and complex data. The expectation (E) step of EM-type algorithms is time-consuming in massive data applications because it requires multiple passes through the full data. We address this problem by proposing an asynchronous and distributed generalization of the EM called the Distributed EM (DEM). Using DEM, existing EM-type algorithms are easily extended to massive data settings by exploiting the divide-and-conquer technique and widely available computing power, such as grid computing. The DEM algorithm reserves two groups of computing processes called \emph{workers} and \emph{managers} for performing the E step and the maximization step (M step), respectively. The samples are randomly partitioned into a large number of disjoint subsets and are stored on the worker processes. The E step of DEM algorithm is performed in parallel on all the workers, and every worker communicates its results to the managers at the end of local E step. The managers perform the M step after they have received results from a $\gamma$-fraction of the workers, where $\gamma$ is a fixed constant in $(0, 1]$. The sequence of parameter estimates generated by the DEM algorithm retains the attractive properties of EM: convergence of the sequence of parameter estimates to a local mode and linear global rate of convergence. Across diverse simulations focused on linear mixed-effects models, the DEM algorithm is significantly faster than competing EM-type algorithms while having a similar accuracy. The DEM algorithm maintains its superior empirical performance on a movie ratings database consisting of 10 million ratings. …

Social Physics (SocioPhysics)
Social physics or sociophysics is a field of science which uses mathematical tools inspired by physics to understand the behavior of human crowds. In a modern commercial use, it can also refer to the analysis of social phenomena with big data. Social physics is closely related to econophysics which uses physics methods to describe economics.
https://www.datasciencecentral.com/profiles/blogs/the-upcoming-revolution-in-predictive-analytics-and-data-science …

Accumulated Total Derivative Effects Plot
Interpreting a nonparametric regression model with many predictors is known to be a challenging problem. There has been renewed interest in this topic due to the extensive use of machine learning algorithms and the difficulty in understanding and explaining their input-output relationships. This paper develops a unified framework using a derivative-based approach for existing tools in the literature, including the partial-dependence plots, marginal plots and accumulated effects plots. It proposes a new interpretation technique called the accumulated total derivative effects plot and demonstrates how its components can be used to develop extensive insights in complex regression models with correlated predictors. The techniques are illustrated through simulation results. …

DN-ResNet
A deep learning approach to blind denoising of images without complete knowledge of the noise statistics is considered. We propose DN-ResNet, which is a deep convolutional neural network (CNN) consisting of several residual blocks (ResBlocks). With cascade training, DN-ResNet is more accurate and more computationally efficient than the state of art denoising networks. An edge-aware loss function is further utilized in training DN-ResNet, so that the denoising results have better perceptive quality compared to conventional loss function. Next, we introduce the depthwise separable DN-ResNet (DS-DN-ResNet) utilizing the proposed Depthwise Seperable ResBlock (DS-ResBlock) instead of standard ResBlock, which has much less computational cost. DS-DN-ResNet is incrementally evolved by replacing the ResBlocks in DN-ResNet by DS-ResBlocks stage by stage. As a result, high accuracy and good computational efficiency are achieved concurrently. Whereas previous state of art deep learning methods focused on denoising either Gaussian or Poisson corrupted images, we consider denoising images having the more practical Poisson with additive Gaussian noise as well. The results show that DN-ResNets are more efficient, robust, and perform better denoising than current state of art deep learning methods, as well as the popular variants of the BM3D algorithm, in cases of blind and non-blind denoising of images corrupted with Poisson, Gaussian or Poisson-Gaussian noise. Our network also works well for other image enhancement task such as compressed image restoration. …

Frobenius Coin Problem
The coin problem (also referred to as the Frobenius coin problem or Frobenius problem, after the mathematician Ferdinand Frobenius) is a mathematical problem that asks for the largest monetary amount that cannot be obtained using only coins of specified denominations. For example, the largest amount that cannot be obtained using only coins of 3 and 5 units is 7 units. The solution to this problem for a given set of coin denominations is called the Frobenius number of the set. The Frobenius number exists as long as the set of coin denominations has no common divisor greater than 1. There is an explicit formula for the Frobenius number when there are only two different coin denominations, x and y: xy – x – y. If the number of coin denominations is three or more, no explicit formula is known; but, for any fixed number of coin denominations, there is an algorithm computing the Frobenius number in polynomial time (in the logarithms of the coin denominations forming an input). No known algorithm is polynomial time in the number of coin denominations, and the general problem, where the number of coin denominations may be as large as desired, is NP-hard. …

Belief Functions
The theory of belief functions provides a non-Bayesian way of using mathematical probability to quantify subjective judgements. Whereas a Bayesian assesses probabilities directly for the answer to a question of interest, a belief-function user assesses probabilities for related questions and then considers the implications of these probabilities for the question of interest. …

Maucha Diagrams
This diagram was proposed by Rezso Maucha in 1932 as a way to vizualise the relative ionic composition of water samples. …

Cycle-Consistent Adversarial GAN (CycleAdvGAN)
In image classification of deep learning, adversarial examples where inputs intended to add small magnitude perturbations may mislead deep neural networks (DNNs) to incorrect results, which means DNNs are vulnerable to them. Different attack and defense strategies have been proposed to better research the mechanism of deep learning. However, those research in these networks are only for one aspect, either an attack or a defense, not considering that attacks and defenses should be interdependent and mutually reinforcing, just like the relationship between spears and shields. In this paper, we propose Cycle-Consistent Adversarial GAN (CycleAdvGAN) to generate adversarial examples, which can learn and approximate the distribution of original instances and adversarial examples. For CycleAdvGAN, once the Generator and are trained, can generate adversarial perturbations efficiently for any instance, so as to make DNNs predict wrong, and recovery adversarial examples to clean instances, so as to make DNNs predict correct. We apply CycleAdvGAN under semi-white box and black-box settings on two public datasets MNIST and CIFAR10. Using the extensive experiments, we show that our method has achieved the state-of-the-art adversarial attack method and also efficiently improve the defense ability, which make the integration of adversarial attack and defense come true. In additional, it has improved attack effect only trained on the adversarial dataset generated by any kind of adversarial attack. …

Deep Multiset Canonical Correlation Analysis (dMCCA)
We propose Deep Multiset Canonical Correlation Analysis (dMCCA) as an extension to representation learning using CCA when the underlying signal is observed across multiple (more than two) modalities. We use deep learning framework to learn non-linear transformations from different modalities to a shared subspace such that the representations maximize the ratio of between- and within-modality covariance of the observations. Unlike linear discriminant analysis, we do not need class information to learn these representations, and we show that this model can be trained for complex data using mini-batches. Using synthetic data experiments, we show that dMCCA can effectively recover the common signal across the different modalities corrupted by multiplicative and additive noise. We also analyze the sensitivity of our model to recover the correlated components with respect to mini-batch size and dimension of the embeddings. Performance evaluation on noisy handwritten datasets shows that our model outperforms other CCA-based approaches and is comparable to deep neural network models trained end-to-end on this dataset. …

Graph Database of Academic Literature (GrapAL)
We introduce GrapAL (Graph database of Academic Literature), a versatile tool for exploring and investigating scientific literature which satisfies a variety of use cases and information needs requested by researchers. At the core of GrapAL is a Neo4j graph database with an intuitive schema and a simple query language. In this paper, we describe the basic elements of GrapAL, how to use it, and several use cases such as finding experts on a given topic for peer reviewing, discovering indirect connections between biomedical entities, and computing citation-based metrics. …

Mixed Formal Learning
This paper presents Mixed Formal Learning, a new architecture that learns models based on formal mathematical representations of the domain of interest and exposes latent variables. The second element in the architecture learns a particular skill, typically by using traditional prediction or classification mechanisms. Our key findings include that this architecture: (1) Facilitates transparency by exposing key latent variables based on a learned mathematical model; (2) Enables Low Shot and Zero Shot training of machine learning without sacrificing accuracy or recall. …

Block Term Network (BT-net)
Recently, deep neural networks (DNNs) have been regarded as the state-of-the-art classification methods in a wide range of applications, especially in image classification. Despite the success, the huge number of parameters blocks its deployment to situations with light computing resources. Researchers resort to the redundancy in the weights of DNNs and attempt to find how fewer parameters can be chosen while preserving the accuracy at the same time. Although several promising results have been shown along this research line, most existing methods either fail to significantly compress a well-trained deep network or require a heavy fine-tuning process for the compressed network to regain the original performance. In this paper, we propose the \textit{Block Term} networks (BT-nets) in which the commonly used fully-connected layers (FC-layers) are replaced with block term layers (BT-layers). In BT-layers, the inputs and the outputs are reshaped into two low-dimensional high-order tensors, then block-term decomposition is applied as tensor operators to connect them. We conduct extensive experiments on benchmark datasets to demonstrate that BT-layers can achieve a very large compression ratio on the number of parameters while preserving the representation power of the original FC-layers as much as possible. Specifically, we can get a higher performance while requiring fewer parameters compared with the tensor train method. …

Rulex
Rulex is a new kind of AI platform, born from advanced government and academic machine learning research, and proven by years of deployment in diverse industries. Rulex´s unique logic-based approach to predictive analytics enables business and process experts to rapidly create and deploy AI applications with no need for math or programming skills. …

Prediction Tournament Paradox
In a prediction tournament, contestants ‘forecast’ by asserting a numerical probability for each of (say) 100 future real-world events. The scoring system is designed so that (regardless of the unknown true probabilities) more accurate forecasters will likely score better. This is true for one-on-one comparisons between contestants. But consider a realistic-size tournament with many contestants, with a range of accuracies. It may seem self-evident that the winner will likely be one of the most accurate forecasters. But, in the setting where the range extends to very accurate forecasters, simulations show this is mathematically false, within a somewhat plausible model. Even outside that setting the winner is less likely than intuition suggests to be one of the handful of best forecasters. Though implicit in recent technical papers, this paradox has apparently not been explicitly pointed out before, though is easily explained. It perhaps has implications for the ongoing IARPA-sponsored research programs involving forecasting. …

FastContext
Objective: To develop and evaluate FastContext, an efficient, scalable implementation of the ConText algorithm suitable for very large-scale clinical natural language processing. Background: The ConText algorithm performs with state-of-art accuracy in detecting the experiencer, negation status, and temporality of concept mentions in clinical narratives. However, the speed limitation of its current implementations hinders its use in big data processing. Methods: We developed FastContext through hashing the ConText’s rules, then compared its speed and accuracy with JavaConText and GeneralConText, two widely used Java implementations. Results: FastContext ran two orders of magnitude faster and was less decelerated by rule increase than the other two implementations used in this study for comparison. Additionally, FastContext consistently gained accuracy improvement as the rules increased (the desired outcome of adding new rules), while the other two implementations did not. Conclusions: FastContext is an efficient, scalable implementation of the popular ConText algorithm, suitable for natural language applications on very large clinical corpora. …

Visual Query Detection (VQD)
We propose Visual Query Detection (VQD), a new visual grounding task. In VQD, a system is guided by natural language to localize a \emph{variable} number of objects in an image. VQD is related to visual referring expression recognition, where the task is to localize only \emph{one} object. We describe the first dataset for VQD and we propose baseline algorithms that demonstrate the difficulty of the task compared to referring expression recognition. …

Fully Hyperbolic Convolutional Neural Networks
Convolutional Neural Networks (CNN) have recently seen tremendous success in various computer vision tasks. However, their application to problems with high dimensional input and output has been limited by two factors. First, in the training stage, it is necessary to store network activations for back propagation. Second, in the inference stage, a few copies of the image are typically stored to be concatenated to other network states deeper in the network. In these settings, the memory requirements associated with storing activations can exceed what is feasible with current hardware. For the problem of image classification, reversible architectures have been proposed that allow one to recalculate activations in the backwards pass instead of storing them, however, such networks do not perform well for problems such as segmentation. Furthermore, currently only block reversible networks have been possible because pooling operations are not reversible. Motivated by the propagation of signals over physical networks, that are governed by the hyperbolic Telegraph equation, in this work we introduce a fully conservative hyperbolic network for problems with high dimensional input and output. We introduce a coarsening operation that allows completely reversible CNNs by using the Discrete Wavelet Transform and its inverse to both coarsen and interpolate the network state and change the number of channels. This means that during training we do not need to store the activations from the forward pass, and can train arbitrarily deep or wide networks. Furthermore, our network has a much lower memory footprint for inference. We show that we are able to achieve results comparable to the state of the art in image classification, depth estimation, and semantic segmentation, with a much lower memory footprint. …

Accelerated Coordinate Descent (ACD)
Accelerated coordinate descent is a widely popular optimization algorithm due to its efficiency on large-dimensional problems. It achieves state-of-the-art complexity on an important class of empirical risk minimization problems. In this paper we design and analyze an accelerated coordinate descent (ACD) method which in each iteration updates a random subset of coordinates according to an arbitrary but fixed probability law, which is a parameter of the method. If all coordinates are updated in each iteration, our method reduces to the classical accelerated gradient descent method AGD of Nesterov. If a single coordinate is updated in each iteration, and we pick probabilities proportional to the square roots of the coordinate-wise Lipschitz constants, our method reduces to the currently fastest coordinate descent method NUACDM of Allen-Zhu, Qu, Richt\'{a}rik and Yuan. While mini-batch variants of ACD are more popular and relevant in practice, there is no importance sampling for ACD that outperforms the standard uniform mini-batch sampling. Through insights enabled by our general analysis, we design new importance sampling for mini-batch ACD which significantly outperforms previous state-of-the-art minibatch ACD in practice. We prove a rate that is at most ${\cal O}(\sqrt{\tau})$ times worse than the rate of minibatch ACD with uniform sampling, but can be ${\cal O}(n/\tau)$ times better, where $\tau$ is the minibatch size. Since in modern supervised learning training systems it is standard practice to choose $\tau \ll n$, and often $\tau={\cal O}(1)$, our method can lead to dramatic speedups. Lastly, we obtain similar results for minibatch nonaccelerated CD as well, achieving improvements on previous best rates. …

CascadeML
Multi-label classification is an approach which allows a datapoint to be labelled with more than one class at the same time. A common but trivial approach is to train individual binary classifiers per label, but the performance can be improved by considering associations within the labels. Like with any machine learning algorithm, hyperparameter tuning is important to train a good multi-label classifier model. The task of selecting the best hyperparameter settings for an algorithm is an optimisation problem. Very limited work has been done on automatic hyperparameter tuning and AutoML in the multi-label domain. This paper attempts to fill this gap by proposing a neural network algorithm, CascadeML, to train multi-label neural network based on cascade neural networks. This method requires minimal or no hyperparameter tuning and also considers pairwise label associations. The cascade algorithm grows the network architecture incrementally in a two phase process as it learns the weights using adaptive first order gradient algorithm, therefore omitting the requirement of preselecting the number of hidden layers, nodes and the learning rate. The method was tested on 10 multi-label datasets and compared with other multi-label classification algorithms. Results show that CascadeML performs very well without hyperparameter tuning. …

Uncertainty Autoencoder
The goal of statistical compressive sensing is to efficiently acquire and reconstruct high-dimensional signals with much fewer measurements than the data dimensionality, given access to a finite set of training signals. Current approaches do not learn the acquisition and recovery procedures end-to-end and are typically hand-crafted for sparsity based priors. We propose Uncertainty Autoencoders, a framework that jointly learns the acquisition (i.e., encoding) and recovery (i.e., decoding) procedures while implicitly modeling domain structure. Our learning objective optimizes for a variational lower bound to the mutual information between the signal and the measurements. We show how our framework provides a unified treatment to several lines of research in dimensionality reduction, compressive sensing, and generative modeling. Empirically, we demonstrate improvements of 32% on average over competing approaches for statistical compressive sensing of high-dimensional datasets. …

Sobolev Training
At the heart of deep learning we aim to use neural networks as function approximators – training them to produce outputs from inputs in emulation of a ground truth function or data creation process. In many cases we only have access to input-output pairs from the ground truth, however it is becoming more common to have access to derivatives of the target output with respect to the input – for example when the ground truth function is itself a neural network such as in network compression or distillation. Generally these target derivatives are not computed, or are ignored. This paper introduces Sobolev Training for neural networks, which is a method for incorporating these target derivatives in addition the to target values while training. By optimising neural networks to not only approximate the function’s outputs but also the function’s derivatives we encode additional information about the target function within the parameters of the neural network. Thereby we can improve the quality of our predictors, as well as the data-efficiency and generalization capabilities of our learned function approximation. We provide theoretical justifications for such an approach as well as examples of empirical evidence on three distinct domains: regression on classical optimisation datasets, distilling policies of an agent playing Atari, and on large-scale applications of synthetic gradients. In all three domains the use of Sobolev Training, employing target derivatives in addition to target values, results in models with higher accuracy and stronger generalisation. …

Functional Isolation Forest (FIF)
For the purpose of monitoring the behavior of complex infrastructures (e.g. aircrafts, transport or energy networks), high-rate sensors are deployed to capture multivariate data, generally unlabeled, in quasi continuous-time to detect quickly the occurrence of anomalies that may jeopardize the smooth operation of the system of interest. The statistical analysis of such massive data of functional nature raises many challenging methodological questions. The primary goal of this paper is to extend the popular Isolation Forest (IF) approach to Anomaly Detection, originally dedicated to finite dimensional observations, to functional data. The major difficulty lies in the wide variety of topological structures that may equip a space of functions and the great variety of patterns that may characterize abnormal curves. We address the issue of (randomly) splitting the functional space in a flexible manner in order to isolate progressively any trajectory from the others, a key ingredient to the efficiency of the algorithm. Beyond a detailed description of the algorithm, computational complexity and stability issues are investigated at length. From the scoring function measuring the degree of abnormality of an observation provided by the proposed variant of the IF algorithm, a Functional Statistical Depth function is defined and discussed as well as a multivariate functional extension. Numerical experiments provide strong empirical evidence of the accuracy of the extension proposed. …

Cognitive Representation Learner (CogRL)
A cognitive model of human learning provides information about skills a learner must acquire to perform accurately in a task domain. Cognitive models of learning are not only of scientific interest, but are also valuable in adaptive online tutoring systems. A more accurate model yields more effective tutoring through better instructional decisions. Prior methods of automated cognitive model discovery have typically focused on well-structured domains, relied on student performance data or involved substantial human knowledge engineering. In this paper, we propose Cognitive Representation Learner (CogRL), a novel framework to learn accurate cognitive models in ill-structured domains with no data and little to no human knowledge engineering. Our contribution is two-fold: firstly, we show that representations learnt using CogRL can be used for accurate automatic cognitive model discovery without using any student performance data in several ill-structured domains: Rumble Blocks, Chinese Character, and Article Selection. This is especially effective and useful in domains where an accurate human-authored cognitive model is unavailable or authoring a cognitive model is difficult. Secondly, for domains where a cognitive model is available, we show that representations learned through CogRL can be used to get accurate estimates of skill difficulty and learning rate parameters without using any student performance data. These estimates are shown to highly correlate with estimates using student performance data on an Article Selection dataset. …

Knowledge Intensive Business Services (KIBS)
Knowledge Intensive Business Services (commonly known as KIBS) are services and business operations heavily reliant on professional knowledge. They are mainly concerned with providing knowledge-intensive support for the business processes of other organizations. As a result, their employment structures are heavily weighted towards scientists, engineers, and other experts. It is common to distinguish between T-KIBS, (those with high use of scientific and technological knowledge – R&D services, engineering services, computer services, etc.), and P-KIBS, who are more traditional professional services – legal, accountancy, and many management consultancy and marketing services. These services either supply products which are themselves primary sources of information and knowledge, or use their specialist knowledge to produce services which facilitate their clients own activities. Consequently, KIBS usually have other businesses as their main clients, though the public sector and sometimes voluntary organisations can be important customers, and to some extent households will feature as consumers of, for instance, legal and accountancy services. …

Domain-to-Domain Translation Model (D2D-TM)
Recently multi-domain recommender systems have received much attention from researchers because they can solve cold-start problem as well as support for cross-selling. However, when applying into multi-domain items, although algorithms specifically addressing a single domain have many difficulties in capturing the specific characteristics of each domain, multi-domain algorithms have less opportunity to obtain similar features among domains. Because both similarities and differences exist among domains, multi-domain models must capture both to achieve good performance. Other studies of multi-domain systems merely transfer knowledge from the source domain to the target domain, so the source domain usually comes from external factors such as the search query or social network, which is sometimes impossible to obtain. To handle the two problems, we propose a model that can extract both homogeneous and divergent features among domains and extract data in a domain can support for other domain equally: a so-called Domain-to-Domain Translation Model (D2D-TM). It is based on generative adversarial networks (GANs), Variational Autoencoders (VAEs), and Cycle-Consistency (CC) for weight-sharing. We use the user interaction history of each domain as input and extract latent features through a VAE-GAN-CC network. Experiments underscore the effectiveness of the proposed system over state-of-the-art methods by a large margin. …

Even Initialization
In this paper, we propose a new weight initialization method called even initialization for wide and deep nonlinear neural networks with the ReLU activation function. We prove that no poor local minimum exists in the initial loss landscape in the wide and deep nonlinear neural network initialized by the even initialization method that we propose. Specifically, in the initial loss landscape of such a wide and deep ReLU neural network model, the following four statements hold true: 1) the loss function is non-convex and non-concave; 2) every local minimum is a global minimum; 3) every critical point that is not a global minimum is a saddle point; and 4) bad saddle points exist. We also show that the weight values initialized by the even initialization method are contained in those initialized by both of the (often used) standard initialization and He initialization methods. …

Wallaroo
Wallaroo is a fast, elastic data processing engine that rapidly takes you from prototype to production by eliminating infrastructure complexity. Wallaroo is a fast and elastic data processing engine that rapidly takes you from prototype to production by making the infrastructure virtually disappear. We´ve designed it to handle demanding high-throughput, low-latency tasks where the accuracy of results is essential. Wallaroo takes care of mechanics of scaling, resilience, state management, and message delivery. We’ve designed Wallaroo to make it easy scale applications with no code changes, and allow programmers to focus on business logic. …

VIREL
Applying probabilistic models to reinforcement learning (RL) has become an exciting direction of research owing to powerful optimisation tools such as variational inference becoming applicable to RL. However, due to their formulation, existing inference frameworks and their algorithms pose significant challenges for learning optimal policies, for example, the absence of mode capturing behaviour in pseudo-likelihood methods and difficulties in optimisation of learning objective in maximum entropy RL based approaches. We propose VIREL, a novel, theoretically grounded probabilistic inference framework for RL that utilises the action-value function in a parametrised form to capture future dynamics of the underlying Markov decision process. Owing to it’s generality, our framework lends itself to current advances in variational inference. Applying the variational expectation-maximisation algorithm to our framework, we show that actor-critic algorithm can be reduced to expectation-maximization. We derive a family of methods from our framework, including state-of-the-art methods based on soft value functions. We evaluate two actor-critic algorithms derived from this family, which perform on par with soft actor critic, demonstrating that our framework offers a promising perspective on RL as inference. …

Maximum Expected Utility
Principle of maximum expected utility: A rational agent should chose the action which maximizes ist expected utility, given its knowledge.
➚ “Expected Utility Hypothesis” …

RDPD
In many situations, we have both rich- and poor- data environments: in a rich-data environment (e.g., intensive care units), we have high-quality multi-modality data. On the other hand, in a poor-data environment (e.g., at home), we often only have access to a single data modality with low quality. How can we learn an accurate and efficient model for the poor-data environment by leveraging multi-modality data from the rich-data environment? In this work, we propose a knowledge distillation model RDPD to enhance a small model trained on poor data with a complex model trained on rich data. In an end-to-end fashion, RDPD trains a student model built on a single modality data (poor data) to imitate the behavior and performance of a teacher model from multimodal data (rich data) via jointly optimizing the combined loss of attention imitation and target imitation. We evaluated RDPD on three real-world datasets. RDPD consistently outperformed all baselines across all three datasets, especially achieving the greatest performance improvement over a standard neural network model trained on the common features (Direct model) by 24.56% on PR-AUC and 12.21% on ROC-AUC, and over the standard knowledge distillation model by 5.91% on PR-AUC and 4.44% on ROC-AUC. …

Jericho
A learning environment for Interactive Fiction games. …

Low-Shot Transfer Detector (LSTD)
Recent advances in object detection are mainly driven by deep learning with large-scale detection benchmarks. However, the fully-annotated training set is often limited for a target detection task, which may deteriorate the performance of deep detectors. To address this challenge, we propose a novel low-shot transfer detector (LSTD) in this paper, where we leverage rich source-domain knowledge to construct an effective target-domain detector with very few training examples. The main contributions are described as follows. First, we design a flexible deep architecture of LSTD to alleviate transfer difficulties in low-shot detection. This architecture can integrate the advantages of both SSD and Faster RCNN in a unified deep framework. Second, we introduce a novel regularized transfer learning framework for low-shot detection, where the transfer knowledge (TK) and background depression (BD) regularizations are proposed to leverage object knowledge respectively from source and target domains, in order to further enhance fine-tuning with a few target images. Finally, we examine our LSTD on a number of challenging low-shot detection experiments, where LSTD outperforms other state-of-the-art approaches. The results demonstrate that LSTD is a preferable deep detector for low-shot scenarios. …

Generalized Matrix Chain Algorithm
In this paper, we present a generalized version of the matrix chain algorithm to generate efficient code for linear algebra problems, a task for which human experts often invest days or even weeks of works. The standard matrix chain problem consists in finding the parenthesization of a matrix product $M := A_1 A_2 \cdots A_n$ that minimizes the number of scalar operations. In practical applications, however, one frequently encounters more complicated expressions, involving transposition, inversion, and matrix properties. Indeed, the computation of such expressions relies on a set of computational kernels that offer functionality well beyond the simple matrix product. The challenge then shifts from finding an optimal parenthesization to finding an optimal mapping of the input expression to the available kernels. Furthermore, it is often the case that a solution based on the minimization of scalar operations does not result in the optimal solution in terms of execution time. In our experiments, the generated code outperforms other libraries and languages on average by a factor of about 9. The motivation for this work comes from the fact that—despite great advances in the development of compilers—the task of mapping linear algebra problems to optimized kernels is still to be done manually. In order to relieve the user from this complex task, new techniques for the compilation of linear algebra expressions have to be developed. …

Fair Top-k Ranking (FA*IR)
We present a formal problem definition and an algorithm to solve the Fair Top-k Ranking problem. The problem consists of creating a ranking of k elements out of a pool of n >> k candidates. The objective is to maximize utility, and maximization is subject to a ranked group fairness constraint. Our definition of ranked group fairness uses the standard notion of protected group to extend the concept of group fairness. It ensures that every prefix of the rank contains a number of protected candidates that is statistically indistinguishable from a given target proportion, or exceeds it. The utility objective favors rankings in which every candidate included in the ranking is more qualified than any candidate not included, and rankings in which candidates are sorted by decreasing qualifications. We describe an efficient algorithm for this problem, which is tested on a series of existing datasets, as well as new datasets. Experimentally, this approach yields a ranking that is similar to the so-called ‘color-blind’ ranking, while respecting the fairness criteria. To the best of our knowledge, FA*IR is the first algorithm grounded in statistical tests that can be used to mitigate biases in ranking against an under-represented group. …

Sequential Deactivation (SDA)
We introduce a new neural network model, together with a tractable and monotone online learning algorithm. Our model describes feed-forward networks for classification, with one output node for each class. The only nonlinear operation is rectification using a ReLU function with a bias. However, there is a rectifier on every edge rather than at the nodes of the network. There are also weights, but these are positive, static, and associated with the nodes. Our ‘rectified wire’ networks are able to represent arbitrary Boolean functions. Only the bias parameters, on the edges of the network, are learned. Another departure in our approach, from standard neural networks, is that the loss function is replaced by a constraint. This constraint is simply that the value of the output node associated with the correct class should be zero. Our model has the property that the exact norm-minimizing parameter update, required to correctly classify a training item, is the solution to a quadratic program that can be computed with a few passes through the network. We demonstrate a training algorithm using this update, called sequential deactivation (SDA), on MNIST and some synthetic datasets. Upon adopting a natural choice for the nodal weights, SDA has no hyperparameters other than those describing the network structure. Our experiments explore behavior with respect to network size and depth in a family of sparse expander networks. …

Zipf’s Law
Zipf’s law, an empirical law formulated using mathematical statistics, refers to the fact that many types of data studied in the physical and social sciences can be approximated with a Zipfian distribution, one of a family of related discrete power law probability distributions. …

Association Rule Mining
➘ “Association Rule Learning” …