Regularization properties of adversarially-trained linear regression

State-of-the-art machine learning models can be vulnerable to very small input perturbations that are adversarially constructed. Adversarial training is an effective approach to defend against it. Formulated as a min-max problem, it searches for the best solution when the training data were corrupted by the worst-case attacks. Linear models are among the simple models where vulnerabilities can be observed and are the focus of our study. In this case, adversarial training leads to a convex optimization problem which can be formulated as the minimization of a finite sum. We provide a comparative analysis between the solution of adversarial training in linear regression and other regularization methods. Our main findings are that: (A) Adversarial training yields the minimum-norm interpolating solution in the overparameterized regime (more parameters than data), as long as the maximum disturbance radius is smaller than a threshold. And, conversely, the minimum-norm interpolator is the solution to adversarial training with a given radius. (B) Adversarial training can be equivalent to parameter shrinking methods (ridge regression and Lasso). This happens in the underparametrized region, for an appropriate choice of adversarial radius and zero-mean symmetrically distributed covariates. (C) For $\ell_\infty$-adversarial training -- as in square-root Lasso -- the choice of adversarial radius for optimal bounds does not depend on the additive noise variance. We confirm our theoretical findings with numerical examples.

End-to-end Risk Prediction of Atrial Fibrillation from the 12-Lead ECG by Deep Neural Networks

Background: Atrial fibrillation (AF) is one of the most common cardiac arrhythmias that affects millions of people each year worldwide and it is closely linked to increased risk of cardiovascular diseases such as stroke and heart failure. Machine learning methods have shown promising results in evaluating the risk of developing atrial fibrillation from the electrocardiogram. We aim to develop and evaluate one such algorithm on a large CODE dataset collected in Brazil. Results: The deep neural network model identified patients without indication of AF in the presented ECG but who will develop AF in the future with an AUC score of 0.845. From our survival model, we obtain that patients in the high-risk group (i.e. with the probability of a future AF case being greater than 0.7) are 50% more likely to develop AF within 40 weeks, while patients belonging to the minimal-risk group (i.e. with the probability of a future AF case being less than or equal to 0.1) have more than 85% chance of remaining AF free up until after seven years. Conclusion: We developed and validated a model for AF risk prediction. If applied in clinical practice, the model possesses the potential of providing valuable and useful information in decision-making and patient management processes.

Deep networks for system identification: a Survey

Deep learning is a topic of considerable current interest. The availability of massive data collections and powerful software resources has led to an impressive amount of results in many application areas that reveal essential but hidden properties of the observations. System identification learns mathematical descriptions of dynamic systems from input-output data and can thus benefit from the advances of deep neural networks to enrich the possible range of models to choose from. For this reason, we provide a survey of deep learning from a system identification perspective. We cover a wide spectrum of topics to enable researchers to understand the methods, providing rigorous practical and theoretical insights into the benefits and challenges of using them. The main aim of the identified model is to predict new data from previous observations. This can be achieved with different deep learning based modelling techniques and we discuss architectures commonly adopted in the literature, like feedforward, convolutional, and recurrent networks. Their parameters have to be estimated from past data trying to optimize the prediction performance. For this purpose, we discuss a specific set of first-order optimization tools that is emerged as efficient. The survey then draws connections to the well-studied area of kernel-based methods. They control the data fit by regularization terms that penalize models not in line with prior assumptions. We illustrate how to cast them in deep architectures to obtain deep kernel-based methods. The success of deep learning also resulted in surprising empirical observations, like the counter-intuitive behaviour of models with many parameters. We discuss the role of overparameterized models, including their connection to kernels, as well as implicit regularization mechanisms which affect generalization, specifically the interesting phenomena of benign overfitting ...

ECG-Based Electrolyte Prediction: Evaluating Regression and Probabilistic Methods

Objective: Imbalances of the electrolyte concentration levels in the body can lead to catastrophic consequences, but accurate and accessible measurements could improve patient outcomes. While blood tests provide accurate measurements, they are invasive and the laboratory analysis can be slow or inaccessible. In contrast, an electrocardiogram (ECG) is a widely adopted tool which is quick and simple to acquire. However, the problem of estimating continuous electrolyte concentrations directly from ECGs is not well-studied. We therefore investigate if regression methods can be used for accurate ECG-based prediction of electrolyte concentrations. Methods: We explore the use of deep neural networks (DNNs) for this task. We analyze the regression performance across four electrolytes, utilizing a novel dataset containing over 290000 ECGs. For improved understanding, we also study the full spectrum from continuous predictions to binary classification of extreme concentration levels. To enhance clinical usefulness, we finally extend to a probabilistic regression approach and evaluate different uncertainty estimates. Results: We find that the performance varies significantly between different electrolytes, which is clinically justified in the interplay of electrolytes and their manifestation in the ECG. We also compare the regression accuracy with that of traditional machine learning models, demonstrating superior performance of DNNs. Conclusion: Discretization can lead to good classification performance, but does not help solve the original problem of predicting continuous concentration levels. While probabilistic regression demonstrates potential practical usefulness, the uncertainty estimates are not particularly well-calibrated. Significance: Our study is a first step towards accurate and reliable ECG-based prediction of electrolyte concentration levels.

On Merging Feature Engineering and Deep Learning for Diagnosis, Risk-Prediction and Age Estimation Based on the 12-Lead ECG

Objective: Machine learning techniques have been used extensively for 12-lead electrocardiogram (ECG) analysis. For physiological time series, deep learning (DL) superiority to feature engineering (FE) approaches based on domain knowledge is still an open question. Moreover, it remains unclear whether combining DL with FE may improve performance. Methods: We considered three tasks intending to address these research gaps: cardiac arrhythmia diagnosis (multiclass-multilabel classification), atrial fibrillation risk prediction (binary classification), and age estimation (regression). We used an overall dataset of 2.3M 12-lead ECG recordings to train the following models for each task: i) a random forest taking the FE as input was trained as a classical machine learning approach; ii) an end-to-end DL model; and iii) a merged model of FE+DL. Results: FE yielded comparable results to DL while necessitating significantly less data for the two classification tasks and it was outperformed by DL for the regression task. For all tasks, merging FE with DL did not improve performance over DL alone. Conclusion: We found that for traditional 12-lead ECG based diagnosis tasks DL did not yield a meaningful improvement over FE, while it improved significantly the nontraditional regression task. We also found that combining FE with DL did not improve over DL alone which suggests that the FE were redundant with the features learned by DL. Significance: Our findings provides important recommendations on what machine learning strategy and data regime to chose with respect to the task at hand for the development of new machine learning models based on the 12-lead ECG.

Surprises in adversarially-trained linear regression

State-of-the-art machine learning models can be vulnerable to very small input perturbations that are adversarially constructed. Adversarial training is one of the most effective approaches to defend against such examples. We show that for linear regression problems, adversarial training can be formulated as a convex problem. This fact is then used to show that $\ell_\infty$-adversarial training produces sparse solutions and has many similarities to the lasso method. Similarly, $\ell_2$-adversarial training has similarities with ridge regression. We use a robust regression framework to analyze and understand these similarities and also point to some differences. Finally, we show how adversarial training behaves differently from other regularization methods when estimating overparameterized models (i.e., models with more parameters than datapoints). It minimizes a sum of three terms which regularizes the solution, but unlike lasso and ridge regression, it can sharply transition into an interpolation mode. We show that for sufficiently many features or sufficiently small regularization parameters, the learned model perfectly interpolates the training data while still exhibiting good out-of-sample performance.

Overparameterized Linear Regression under Adversarial Attacks

As machine learning models start to be used in critical applications, their vulnerabilities and brittleness become a pressing concern. Adversarial attacks are a popular framework for studying these vulnerabilities. In this work, we study the error of linear regression in the face of adversarial attacks. We provide bounds of the error in terms of the traditional risk and the parameter norm and show how these bounds can be leveraged and make it possible to use analysis from non-adversarial setups to study the adversarial risk. The usefulness of these results is illustrated by shedding light on whether or not overparameterized linear models can be adversarially robust. We show that adding features to linear models might be either a source of additional robustness or brittleness. We show that these differences appear due to scaling and how the $\ell_1$ and $\ell_2$ norms of random projections concentrate. We also show how the reformulation we propose allows for solving adversarial training as a convex optimization problem. This is then used as a tool to study how adversarial training and other regularization methods might affect the robustness of the estimated models.

How Convolutional Neural Networks Deal with Aliasing

The convolutional neural network (CNN) remains an essential tool in solving computer vision problems. Standard convolutional architectures consist of stacked layers of operations that progressively downscale the image. Aliasing is a well-known side-effect of downsampling that may take place: it causes high-frequency components of the original signal to become indistinguishable from its low-frequency components. While downsampling takes place in the max-pooling layers or in the strided-convolutions in these models, there is no explicit mechanism that prevents aliasing from taking place in these layers. Due to the impressive performance of these models, it is natural to suspect that they, somehow, implicitly deal with this distortion. The question we aim to answer in this paper is simply: "how and to what extent do CNNs counteract aliasing?" We explore the question by means of two examples: In the first, we assess the CNNs capability of distinguishing oscillations at the input, showing that the redundancies in the intermediate channels play an important role in succeeding at the task; In the second, we show that an image classifier CNN while, in principle, capable of implementing anti-aliasing filters, does not prevent aliasing from taking place in the intermediate layers.

Beyond Occam's Razor in System Identification: Double-Descent when Modeling Dynamics

System identification aims to build models of dynamical systems from data. Traditionally, choosing the model requires the designer to balance between two goals of conflicting nature; the model must be rich enough to capture the system dynamics, but not so flexible that it learns spurious random effects from the dataset. It is typically observed that model validation performance follows a U-shaped curve as the model complexity increases. Recent developments in machine learning and statistics, however, have observed situations where a "double-descent" curve subsumes this U-shaped model-performance curve. With a second decrease in performance occurring beyond the point where the model has reached the capacity of interpolating - i.e., (near) perfectly fitting - the training data. To the best of our knowledge, however, such phenomena have not been studied within the context of the identification of dynamic systems. The present paper aims to answer the question: "Can such a phenomenon also be observed when estimating parameters of dynamic systems?" We show the answer is yes, verifying such behavior experimentally both for artificially generated and real-world datasets.

Deep Energy-Based NARX Models

This paper is directed towards the problem of learning nonlinear ARX models based on system input--output data. In particular, our interest is in learning a conditional distribution of the current output based on a finite window of past inputs and outputs. To achieve this, we consider the use of so-called energy-based models, which have been developed in allied fields for learning unknown distributions based on data. This energy-based model relies on a general function to describe the distribution, and here we consider a deep neural network for this purpose. The primary benefit of this approach is that it is capable of learning both simple and highly complex noise models, which we demonstrate on simulated and experimental data.