Ridge regression (RR) is a regularization technique that penalizes the L2-norm of the coefficients in linear regression. One of the challenges of using RR is the need to set a hyperparameter ($\alpha$) that controls the amount of regularization. Cross-validation is typically used to select the best $\alpha$ from a set of candidates. However, efficient and appropriate selection of $\alpha$ can be challenging, particularly where large amounts of data are analyzed. Because the selected $\alpha$ depends on the scale of the data and predictors, it is not straightforwardly interpretable. Here, we propose to reparameterize RR in terms of the ratio $\gamma$ between the L2-norms of the regularized and unregularized coefficients. This approach, called fractional RR (FRR), has several benefits: the solutions obtained for different $\gamma$ are guaranteed to vary, guarding against wasted calculations, and automatically span the relevant range of regularization, avoiding the need for arduous manual exploration. We provide an algorithm to solve FRR, as well as open-source software implementations in Python and MATLAB (https://github.com/nrdg/fracridge). We show that the proposed method is fast and scalable for large-scale data problems, and delivers results that are straightforward to interpret and compare across models and datasets.

Crowdsourcing is a popular approach to collect annotations for unlabeled data instances. It involves collecting a large number of annotations from several, often naive untrained annotators for each data instance which are then combined to estimate the ground truth. Further, annotations for constructs such as affect are often multi-dimensional with annotators rating multiple dimensions, such as valence and arousal, for each instance. Most annotation fusion schemes however ignore this aspect and model each dimension separately. In this work we address this by proposing a generative model for multi-dimensional annotation fusion, which models the dimensions jointly leading to more accurate ground truth estimates. The model we propose is applicable to both global and time series annotation fusion problems and treats the ground truth as a latent variable distorted by the annotators. The model parameters are estimated using the Expectation-Maximization algorithm and we evaluate its performance using synthetic data and real emotion corpora as well as on an artificial task with human annotations

The federal government has received plenty of well-deserved flack for slow-rolling the national launch of diagnostic tests for Covid-19. First came the flawed swab-based tests from the Centers for Disease Control and Prevention, followed by a chaotic, lost month of regulatory tango that prevented independent tests from getting scaled and out the door. So when interest arose in a different kind of testing--antibody blood tests, which are used to find evidence of past infection, not a current diagnosis--the US Food and Drug Administration was under pressure to hurry things along. In mid-March, the agency loosened its rules, declaring via an update to its emergency use guidance that antibody tests could be sold without seeking the agency's approval, provided that manufacturers did their own validation. Now FDA officials are walking back that decision.

The right to be forgotten states that a data owner has the right to erase her data from an entity storing it. In the context of machine learning (ML), the right to be forgotten requires an ML model owner to remove the data owner's data from the training set used to build the ML model, a process known as machine unlearning. While originally designed to protect the privacy of the data owner, we argue that machine unlearning may leave some imprint of the data in the ML model and thus create unintended privacy risks. In this paper, we perform the first study on investigating the unintended information leakage caused by machine unlearning. We propose a novel membership inference attack which leverages the different outputs of an ML model's two versions to infer whether the deleted sample is part of the training set. Our experiments over five different datasets demonstrate that the proposed membership inference attack achieves strong performance. More importantly, we show that our attack in multiple cases outperforms the classical membership inference attack on the original ML model, which indicates that machine unlearning can have counterproductive effects on privacy. We notice that the privacy degradation is especially significant for well-generalized ML models where classical membership inference does not perform well. We further investigate two mechanisms to mitigate the newly discovered privacy risks and show that the only effective mechanism is to release the predicted label only. We believe that our results can help improve privacy in practical implementation of machine unlearning.

Recognition of anomalous events is a challenging but critical task in many scientific and industrial fields, especially when the properties of anomalies are unknown. In this paper, we present a new anomaly concept called "unicorn" or unique event and present a new, model-independent, unsupervised detection algorithm to detect unicorns. The Temporal Outlier Factor (TOF) is introduced to measure the uniqueness of events in continuous data sets from dynamic systems. The concept of unique events differs significantly from traditional outliers in many aspects: while repetitive outliers are no longer unique events, a unique event is not necessarily outlier in either pointwise or collective sense; it does not necessarily fall out from the distribution of normal activity. The performance of our algorithm was examined in recognizing unique events on different types of simulated data sets with anomalies and it was compared with the standard Local Outlier Factor (LOF). TOF had superior performance compared to LOF even in recognizing traditional outliers and it also recognized unique events that LOF did not. Benefits of the unicorn concept and the new detection method were illustrated by example data sets from very different scientific fields. Our algorithm successfully recognized unique events in those cases where they were already known such as the gravitational waves of a black hole merger on LIGO detector data and the signs of respiratory failure on ECG data series. Furthermore, unique events were found on the LIBOR data set of the last 30 years.

As the new coronavirus burns its way across the world, scientists are rushing to find ways to identify those who have been infected -- including those who have recovered from COVID-19. Those people, the thinking goes, may be immune to the deadly virus and could theoretically help restart the economy without fear of reinfection. One key piece of this puzzle is rolling out what are known as serological tests that look for specific antibodies in a person's blood. So far, they have been used to estimate how much of the population has been exposed in different areas, such as New York City and Los Angeles. But what are these tests, and can they really help to identify who is immune to SARS-CoV-2? From how they work to what they tell us, here's everything you need to know about coronavirus antibody testing.

Recently, I have been working on a binary classification problem with an imbalanced dataset, where the ratio of positive class to negative class is around 1:4. Imbalanced classification problems are so commonplace that data enthusiasts would encounter them sooner or later. In this post, I will be sharing three tree-based Machine Learning Models that can help handle imbalanced datasets. The dataset that I am going to use to illustrate the effectiveness of algorithms is the credit card fraud dataset from Kaggle. This is an extremely imbalanced dataset: out of 284,807 transactions, there are only 492 frauds. Following the convention, we label the fraud class samples as positive class and normal transactions, negative class.

Machine-learning algorithms trained on features extracted from static code analysis can successfully detect Android malware. However, these approaches can be evaded by sparse evasion attacks that produce adversarial malware samples in which only few features are modified. This can be achieved, e.g., by injecting a small set of fake permissions and system calls into the malicious application, without compromising its intrusive functionality. To improve adversarial robustness against such sparse attacks, learning algorithms should avoid providing decisions which only rely upon a small subset of discriminant features; otherwise, even manipulating some of them may easily allow evading detection. Previous work showed that classifiers which avoid overemphasizing few discriminant features tend to be more robust against sparse attacks, and have developed simple metrics to help identify and select more robust algorithms. In this work, we aim to investigate whether gradient-based attribution methods used to explain classifiers' decisions by identifying the most relevant features can also be used to this end. Our intuition is that a classifier providing more uniform, evener attributions should rely upon a larger set of features, instead of overemphasizing few of them, thus being more robust against sparse attacks. We empirically investigate the connection between gradient-based explanations and adversarial robustness on a case study conducted on Android malware detection, and show that, in some cases, there is a strong correlation between the distribution of such explanations and adversarial robustness. We conclude the paper by discussing how our findings may thus enable the development of more efficient mechanisms both to evaluate and to improve adversarial robustness.

Despite the potential of Machine learning (ML) to learn the behavior of malware, detect novel malware samples, and significantly improve information security (InfoSec) we see few, if any, high-impact ML techniques in deployed systems, notwithstanding multiple reported successes in open literature. We hypothesize that the failure of ML in making high-impacts in InfoSec are rooted in a disconnect between the two communities as evidenced by a semantic gap---a difference in how executables are described (e.g. the data and features extracted from the data). Specifically, current datasets and representations used by ML are not suitable for learning the behaviors of an executable and differ significantly from those used by the InfoSec community. In this paper, we survey existing datasets used for classifying malware by ML algorithms and the features that are extracted from the data. We observe that: 1) the current set of extracted features are primarily syntactic, not behavioral, 2) datasets generally contain extreme exemplars producing a dataset in which it is easy to discriminate classes, and 3) the datasets provide significantly different representations of the data encountered in real-world systems. For ML to make more of an impact in the InfoSec community requires a change in the data (including the features and labels) that is used to bridge the current semantic gap. As a first step in enabling more behavioral analyses, we label existing malware datasets with behavioral features using open-source threat reports associated with malware families. This behavioral labeling alters the analysis from identifying intent (e.g. good vs bad) or malware family membership to an analysis of which behaviors are exhibited by an executable. We offer the annotations with the hope of inspiring future improvements in the data that will further bridge the semantic gap between the ML and InfoSec communities.

Gradient-domain machine learning (GDML) is an accurate and efficient approach to learn a molecular potential and associated force field based on the kernel ridge regression algorithm. Here, we demonstrate its application to learn an effective coarse-grained (CG) model from all-atom simulation data in a sample efficient manner. The coarse-grained force field is learned by following the thermodynamic consistency principle, here by minimizing the error between the predicted coarse-grained force and the all-atom mean force in the coarse-grained coordinates. Solving this problem by GDML directly is impossible because coarse-graining requires averaging over many training data points, resulting in impractical memory requirements for storing the kernel matrices. In this work, we propose a data-efficient and memory-saving alternative. Using ensemble learning and stratified sampling, we propose a 2-layer training scheme that enables GDML to learn an effective coarse-grained model. We illustrate our method on a simple biomolecular system, alanine dipeptide, by reconstructing the free energy landscape of a coarse-grained variant of this molecule. Our novel GDML training scheme yields a smaller free energy error than neural networks when the training set is small, and a comparably high accuracy when the training set is sufficiently large.