Despite the wide empirical success of modern machine learning algorithms and models in a multitude of applications, they are known to be highly susceptible to seemingly small indiscernible perturbations to the input data known as adversarial attacks. A variety of recent adversarial training procedures have been proposed to remedy this issue. Despite the success of such procedures at increasing accuracy on adversarially perturbed inputs or robust accuracy, these techniques often reduce accuracy on natural unperturbed inputs or standard accuracy. Complicating matters further the effect and trend of adversarial training procedures on standard and robust accuracy is rather counter intuitive and radically dependent on a variety of factors including the perceived form of the perturbation during training, size/quality of data, model overparameterization, etc. In this paper we focus on binary classification problems where the data is generated according to the mixture of two Gaussians with general anisotropic covariance matrices and derive a precise characterization of the standard and robust accuracy for a class of minimax adversarially trained models. We consider a general norm-based adversarial model, where the adversary can add perturbations of bounded $\ell_p$ norm to each input data, for an arbitrary $p\ge 1$. Our comprehensive analysis allows us to theoretically explain several intriguing empirical phenomena and provide a precise understanding of the role of different problem parameters on standard and robust accuracies.

The traditional binary classification framework constructs classifiers which may have good accuracy, but whose false positive and false negative error rates are not under users' control. In many cases, one of the errors is more severe and only the classifiers with the corresponding rate lower than the predefined threshold are acceptable. In this study, we combine binary classification with statistical hypothesis testing to control the target error rate of already trained classifiers. In particular, we show how to turn binary classifiers into statistical tests, calculate the classification p-values, and use them to limit the target error rate.

Novelty detection, i.e., identifying whether a given sample is drawn from outside the training distribution, is essential for reliable machine learning. To this end, there have been many attempts at learning a representation well-suited for novelty detection and designing a score based on such representation. In this paper, we propose a simple, yet effective method named contrasting shifted instances (CSI), inspired by the recent success on contrastive learning of visual representations. Specifically, in addition to contrasting a given sample with other instances as in conventional contrastive learning methods, our training scheme contrasts the sample with distributionally-shifted augmentations of itself. Based on this, we propose a new detection score that is specific to the proposed training scheme. Our experiments demonstrate the superiority of our method under various novelty detection scenarios, including unlabeled one-class, unlabeled multi-class and labeled multi-class settings, with various image benchmark datasets. Code and pre-trained models are available at https://github.com/alinlab/CSI.

Existing work on object detection often relies on a single form of annotation: the model is trained using either accurate yet costly bounding boxes or cheaper but less expressive image-level tags. However, real-world annotations are often diverse in form, which challenges these existing works. In this paper, we present UFO$^2$, a unified object detection framework that can handle different forms of supervision simultaneously. Specifically, UFO$^2$ incorporates strong supervision (e.g., boxes), various forms of partial supervision (e.g., class tags, points, and scribbles), and unlabeled data. Through rigorous evaluations, we demonstrate that each form of label can be utilized to either train a model from scratch or to further improve a pre-trained model. We also use UFO$^2$ to investigate budget-aware omni-supervised learning, i.e., various annotation policies are studied under a fixed annotation budget: we show that competitive performance needs no strong labels for all data. Finally, we demonstrate the generalization of UFO$^2$, detecting more than 1,000 different objects without bounding box annotations.

Eight technologies developed by MIT Lincoln Laboratory researchers, either wholly or in collaboration with researchers from other organizations, were among the winners of the 2020 R&D 100 Awards. Annually since 1963, these international R&D awards recognize 100 technologies that a panel of expert judges selects as the most revolutionary of the past year. Six of the laboratory's winning technologies are software systems, a number of which take advantage of artificial intelligence techniques. The software technologies are solutions to difficulties inherent in analyzing large volumes of data and to problems in maintaining cybersecurity. Another technology is a process designed to assure secure fabrication of integrated circuits, and the eighth winner is an optical communications technology that may enable future space missions to transmit error-free data to Earth at significantly higher rates than currently possible.

The year 2020 has seen the COVID-19 virus lead to one of the worst global pandemics in history. As a result, governments around the world are faced with the challenge of protecting public health, while keeping the economy running to the greatest extent possible. Epidemiological models provide insight into the spread of these types of diseases and predict the effects of possible intervention policies. However, to date,the even the most data-driven intervention policies rely on heuristics. In this paper, we study how reinforcement learning (RL) can be used to optimize mitigation policies that minimize the economic impact without overwhelming the hospital capacity. Our main contributions are (1) a novel agent-based pandemic simulator which, unlike traditional models, is able to model fine-grained interactions among people at specific locations in a community; and (2) an RL-based methodology for optimizing fine-grained mitigation policies within this simulator. Our results validate both the overall simulator behavior and the learned policies under realistic conditions.

Provenance is a record that describes how entities, activities, and agents have influenced a piece of data. Such provenance information is commonly represented in graphs with relevant labels on both their nodes and edges. With the growing adoption of provenance in a wide range of application domains, increasingly, users are confronted with an abundance of graph data, which may prove challenging to analyse. Graph kernels, on the other hand, have been consistently and successfully used to efficiently classify graphs. In this paper, we introduce a novel graph kernel called \emph{provenance kernel}, which is inspired by and tailored for provenance data. It decomposes a provenance graph into tree-patterns rooted at a given node and considers the labels of edges and nodes up to a certain distance from the root. We employ provenance kernels to classify provenance graphs from three application domains. Our evaluation shows that they perform well in terms of classification accuracy and yield competitive results when compared against standard graph kernel methods and the provenance network analytics method while taking significantly less time.Moreover, we illustrate how the provenance types used in provenance kernels help improve the explainability of predictive models.

Procedures are an important knowledge component of documents that can be leveraged by cognitive assistants for automation, question-answering or driving a conversation. It is a challenging problem to parse big dense documents like product manuals, user guides to automatically understand which parts are talking about procedures and subsequently extract them. Most of the existing research has focused on extracting flows in given procedures or understanding the procedures in order to answer conceptual questions. Identifying and extracting multiple procedures automatically from documents of diverse formats remains a relatively less addressed problem. In this work, we cover some of this ground by -- 1) Providing insights on how structural and linguistic properties of documents can be grouped to define types of procedures, 2) Analyzing documents to extract the relevant linguistic and structural properties, and 3) Formulating procedure identification as a classification problem that leverages the features of the document derived from the above analysis. We first implemented and deployed unsupervised techniques which were used in different use cases. Based on the evaluation in different use cases, we figured out the weaknesses of the unsupervised approach. We then designed an improved version which was supervised. We demonstrate that our technique is effective in identifying procedures from big and complex documents alike by achieving accuracy of 89%.

Almost every machine learning algorithm comes with a large number of settings that we, the machine learning researchers and practitioners, need to specify. These tuning knobs, the so-called hyperparameters, help us control the behavior of machine learning algorithms when optimizing for performance, finding the right balance between bias and variance. Hyperparameter tuning for performance optimization is an art in itself, and there are no hard-and-fast rules that guarantee best performance on a given dataset. In Part I and Part II, we saw different holdout and bootstrap techniques for estimating the generalization performance of a model. We learned about the bias-variance trade-off, and we computed the uncertainty of our estimates.

Nonparametric two-sample tests for equality of distributions are widely studied in statistics, driven by applications in goodness-of-fit tests, anomaly and change-point detection and clustering. Classical examples of such tests include the Kolmogorov-Smirnov test [41, 69, 62] and Wald-Wolfowitz runs test [84] with subsequent multivariate extensions [25]. Due to advances in the ability to collect large amounts of real time or spatially distributed data there is a need to develop statistical methods appropriate for functional data, where each data sample is a discretised function. Such data has been studied for decades in the Functional Data Analysis (FDA) literature [32, 35] particularly in the context of analysing populations of time series, or in statistical shape analysis [45]. More recently, due to this modern abundance of functional data, increased study has been made in the machine learning literature for algorithms suited to such data [7, 15, 37, 12, 88].