It is common practice in using regression type models for inferring causal effects, that inferring the correct causal relationship requires extra covariates are included or ``adjusted for''. Without performing this adjustment erroneous causal effects can be inferred. Given this phenomenon it is common practice to include as many covariates as possible, however such advice comes unstuck in the presence of M-bias. M-Bias is a problem in causal inference where the correct estimation of treatment effects requires that certain variables are not adjusted for i.e. are simply neglected from inclusion in the model. This issue caused a storm of controversy in 2009 when Rubin, Pearl and others disagreed about if it could be problematic to include additional variables in models when inferring causal effects. This paper makes two contributions to this issue. Firstly we provide a Bayesian solution to the M-Bias problem. The solution replicates Pearl's solution, but consistent with Rubin's advice we condition on all variables. Secondly the fact that we are able to offer a solution to this problem in Bayesian terms shows that it is indeed possible to represent causal relationships within the Bayesian paradigm, albeit in an extended space. We make several remarks on the similarities and differences between causal graphical models which implement the do-calculus and probabilistic graphical models which enable Bayesian statistics. We hope this work will stimulate more research on unifying Pearl's causal calculus using causal graphical models with traditional Bayesian statistics and probabilistic graphical models.

Machine learning and data mining techniques have been used extensively in order to detect credit card frauds. However purchase behaviour and fraudster strategies may change over time. This phenomenon is named dataset shift or concept drift in the domain of fraud detection. In this paper, we present a method to quantify day-by-day the dataset shift in our face-to-face credit card transactions dataset (card holder located in the shop) . In practice, we classify the days against each other and measure the efficiency of the classification. The more efficient the classification, the more different the buying behaviour between two days, and vice versa. Therefore, we obtain a distance matrix characterizing the dataset shift. After an agglomerative clustering of the distance matrix, we observe that the dataset shift pattern matches the calendar events for this time period (holidays, week-ends, etc). We then incorporate this dataset shift knowledge in the credit card fraud detection task as a new feature. This leads to a small improvement of the detection.

Topological Data Analysis (TDA) is a recent approach to analyze data sets from the perspective of their topological structure. Its use for time series data has been limited to the field of financial time series primarily and as a method for feature generation in machine learning applications. In this work, TDA is presented as a technique to gain additional understanding of the customers' loyalty for business-to-business customer relationship management. Increasing loyalty and strengthening relationships with key accounts remain an active topic of discussion both for researchers and managers. Using two public and two proprietary data sets of commercial data, this research shows that the technique enables analysts to better understand their customer base and identify prospective opportunities. In addition, the approach can be used as a clustering method to increase the accuracy of a predictive model for loyalty scoring. This work thus seeks to introduce TDA as a viable tool for data analysis to the quantitate marketing practitioner.

More and more AI services are provided through APIs on cloud where predictive models are hidden behind APIs. To build trust with users and reduce potential application risk, it is important to interpret how such predictive models hidden behind APIs make their decisions. The biggest challenge of interpreting such predictions is that no access to model parameters or training data is available. Existing works interpret the predictions of a model hidden behind an API by heuristically probing the response of the API with perturbed input instances. However, these methods do not provide any guarantee on the exactness and consistency of their interpretations. In this paper, we propose an elegant closed form solution named \texttt{OpenAPI} to compute exact and consistent interpretations for the family of Piecewise Linear Models (PLM), which includes many popular classification models. The major idea is to first construct a set of overdetermined linear equation systems with a small set of perturbed instances and the predictions made by the model on those instances. Then, we solve the equation systems to identify the decision features that are responsible for the prediction on an input instance. Our extensive experiments clearly demonstrate the exactness and consistency of our method.

As Machine Learning (ML) becomes pervasive in various real world systems, the need for models to be interpretable or explainable has increased. We focus on interpretability, noting that models often need to be constrained in size for them to be considered understandable, e.g., a decision tree of depth 5 is easier to interpret than one of depth 50. This suggests a trade-off between interpretability and accuracy. We propose a technique to minimize this tradeoff. Our strategy is to first learn a powerful, possibly black-box, probabilistic model on the data, which we refer to as the oracle. We use this to adaptively sample the training dataset to present data to our model of interest to learn from. Determining the sampling strategy is formulated as an optimization problem that, independent of the dimensionality of the data, uses only seven variables. We empirically show that this often significantly increases the accuracy of our model. Our technique is model agnostic - in that, both the interpretable model and the oracle might come from any model family. Results using multiple real world datasets, using Linear Probability Models and Decision Trees as interpretable models, and Gradient Boosted Model and Random Forest as oracles are presented. Additionally, we discuss an interesting example of using a sentence-embedding based text classifier as an oracle to improve the accuracy of a term-frequency based bag-of-words linear classifier.

We establish a theoretical link between adversarial training and operator norm regularization for deep neural networks. Specifically, we show that adversarial training is a data-dependent generalization of spectral norm regularization. This intriguing connection provides fundamental insights into the origin of adversarial vulnerability and hints at novel ways to robustify and defend against adversarial attacks. We provide extensive empirical evidence to support our theoretical results.

This paper presents our contribution to PolEval 2019 Task 6: Hate speech and bullying detection. We describe three parallel approaches that we followed: fine-tuning a pre-trained ULMFiT model to our classification task, fine-tuning a pre-trained BERT model to our classification task, and using the TPOT library to find the optimal pipeline. We present results achieved by these three tools and review their advantages and disadvantages in terms of user experience. Our team placed second in subtask 2 with a shallow model found by TPOT: a~logistic regression classifier with non-trivial feature engineering.

Mining and exploring databases should provide users with knowledge and new insights. Tiles of data strive to unveil true underlying structure and distinguish valuable information from various kinds of noise. We propose a novel Boolean matrix factorization algorithm to solve the tiling problem, based on recent results from optimization theory. In contrast to existing work, the new algorithm minimizes the description length of the resulting factorization. This approach is well known for model selection and data compression, but not for finding suitable factorizations via numerical optimization. We demonstrate the superior robustness of the new approach in the presence of several kinds of noise and types of underlying structure. Moreover, our general framework can work with any cost measure having a suitable real-valued relaxation. Thereby, no convexity assumptions have to be met. The experimental results on synthetic data and image data show that the new method identifies interpretable patterns which explain the data almost always better than the competing algorithms.

We consider minimizing a nonconvex, smooth function $f$ on a Riemannian manifold $\mathcal{M}$. We show that a perturbed version of Riemannian gradient descent algorithm converges to a second-order stationary point (and hence is able to escape saddle points on the manifold). The rate of convergence depends as $1/\epsilon^2$ on the accuracy $\epsilon$, which matches a rate known only for unconstrained smooth minimization. The convergence rate depends polylogarithmically on the manifold dimension $d$, hence is almost dimension-free. The rate also has a polynomial dependence on the parameters describing the curvature of the manifold and the smoothness of the function. While the unconstrained problem (Euclidean setting) is well-studied, our result is the first to prove such a rate for nonconvex, manifold-constrained problems.

Understanding if classifiers generalize to out-of-sample datasets is a central problem in machine learning. Microscopy images provide a standardized way to measure the generalization capacity of image classifiers, as we can image the same classes of objects under increasingly divergent, but controlled factors of variation. We created a public dataset of 132,209 images of mouse cells, COOS-7 (Cells Out Of Sample 7-Class). COOS-7 provides a classification setting where four test datasets have increasing degrees of covariate shift: some images are random subsets of the training data, while others are from experiments reproduced months later and imaged by different instruments. We benchmarked a range of classification models using different representations, including transferred neural network features, end-to-end classification with a supervised deep CNN, and features from a self-supervised CNN. While most classifiers perform well on test datasets similar to the training dataset, all classifiers failed to generalize their performance to datasets with greater covariate shifts. These baselines highlight the challenges of covariate shifts in image data, and establish metrics for improving the generalization capacity of image classifiers.