Linear time-invariant (LTI) systems find ubiquitous applications in digital signal processing [1], image processing [2], communication [3], and array processing [4], to name a few. An LTI system can be characterized by its impulse response, which is defined as the output response to an impulse input. For an arbitrary input signal, the output signal of an LTI system is obtained by the convolution of

Optimization lies at the heart of machine learning (ML) and signal processing (SP). Contemporary approaches based on the stochastic gradient (SG) method are nonadaptive in the sense that their implementation employs prescribed parameter values that need to be tuned for each application. This article summarizes recent research and motivates future work on adaptive stochastic optimization methods, which

During the past 20 years, low-rank tensor and matrix decomposition models (LRDMs) have become indispensable tools for signal processing, machine learning, and data science. LRDMs represent high-dimensional, multiaspect, and multimodal data using low-dimensional latent factors in a succinct and parsimonious way. LRDMs can serve a variety of purposes, e.g., data embedding (dimensionality reduction),

One of the major concerns for neural network training is that the nonconvexity of the associated loss functions may cause a bad landscape. The recent success of neural networks suggests that their loss landscape is not too bad, but what specific results do we know about the landscape? In this article, we review recent findings and results on the global landscape of neural networks.

Aimed at both casual spectators and active participants of optimization on manifolds alike, this introductory article presents a wide range of information I would have liked to have been told when I first entered the field. Several arguments are put forth: 1) it is not true that nonconvex implies difficult, 2) many optimization problems in signal processing are approached from the wrong perspective

Presents the front cover for this issue of the publication.

Presents the table of contents for this issue of the publication.

Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.

Presents the President’s message for this issue of the publication.

Reports on new SPS society editors-in-chief.

Presents information on the electrion of SPS society Regional Directors-at-Large and Members-at-Large.

Presents a list of articles published by the IEEE Signal Processing Society (SPS) that ranked among the top 100 most downloaded IEEE Xplore articles.

Whether being developed for entertainment, environmental monitoring, exploration, or any of a wide range of other applications, advanced imaging technologies are literally changing the way people see things. In virtually all areas of imaging innovation, signal processing is an essential tool that helps researchers craft technologies that once existed only in the realms of fantasy and science fiction

Presents information on the IEEE Video and Image Processing Cup VIP Cup 2020.

The articles in this special section focus on nonconvex optimization for signal processing and machine learning. Optimization is now widely recognized as an indispensable tool in signal processing (SP) and machine learning (ML). Indeed, many of the advances in these fields rely crucially on the formulation of suitable optimization models and deployment of efficient numerical optimization algorithms

Many contemporary applications in signal processing and machine learning give rise to structured nonconvex nonsmooth optimization problems that can often be tackled by simple iterative methods quite effectively. One of the keys to understanding such a phenomenon-and, in fact, a very difficult conundrum even for experts-lies in the study of "stationary points" of the problem in question. Unlike smooth

Zeroth-order (ZO) optimization is a subset of gradient-free optimization that emerges in many signal processing and machine learning (ML) applications. It is used for solving optimization problems similarly to gradient-based methods. However, it does not require the gradient, using only function evaluations. Specifically, ZO optimization iteratively performs three major steps: gradient estimation,

The min-max optimization problem, also known as the saddle point problem, is a classical optimization problem that is also studied in the context of zero-sum games. Given a class of objective functions, the goal is to find a value for the argument that leads to a small objective value even for the worst-case function in the given class. Min-max optimization problems have recently become very popular

Phase retrieval (PR), also sometimes referred to as quadratic sensing, is a problem that occurs in numerous signal and image acquisition domains ranging from optics, X-ray crystallography, Fourier ptychography, subdiffraction imaging, and astronomy. In each of these domains, the physics of the acquisition system dictates that only the magnitude (intensity) of certain linear projections of the signal

Submodularity is a discrete domain functional property that can be interpreted as mimicking the role of well-known convexity/concavity properties in the continuous domain. Submodular functions exhibit strong structure that lead to efficient optimization algorithms with provable near-optimality guarantees. These characteristics, namely, efficiency and provable performance bounds, are of particular interest

Deep learning has proven itself to be a powerful tool to develop datadriven signal processing algorithms for challenging engineering problems. By learning the key features and characteristics of the input signals instead of requiring a human to first identify and model them, learned algorithms can beat many human-made algorithms. In particular, deep neural networks are capable of learning the complicated

Presents information on the ICASSP 2020 Conference.

Presents highlights from the Highlights from the 2020 IEEE Signal Processing Cup student competition.

Presents highlights from the SPS society 2020 IEEE Five-Minute Video Clip Contest.

Presents the SPS society calendar of upcoming events and meetings.

Presents the introductory editorial for this issue of the publication.

As a bio-inspired and emerging sensor, an event-based neuromorphic vision sensor has a different working principle compared to the standard frame-based cameras, which leads to promising properties of low energy consumption, low latency, high dynamic range (HDR), and high temporal resolution. It poses a paradigm shift to sense and perceive the environment by capturing local pixel-level light intensity

Presents the front cover for this issue of the publication.

Prospective authors are requested to submit new, unpublished manuscripts for inclusion in the upcoming event described in this call for papers.

Presents the table of contents for this issue of the publication.

Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.

Presents the President’s message for this issue of the publication.

Oceans cover approximately 71% of Earth's surface yet remain difficult to explore and monitor remotely. Communication challenges, including lengthy propagation delays, Doppler effects due to vehicle and water movement, and the highly dynamic multipath nature of the undersea environment, can result in significant errors and outliers in transmissions, received data measurements, and image analysis.

The articles in this special section were focused on the current state of the art as well as emerging trends in the design, development, and deployment of sensing and perception technologies for autonomous and automated driving. Such technologies include camera, ultrasound, Global Navigation Satellite System-, lidar-, and radar-based platforms integrat ing signa l processing components to process the

Autonomous vehicles (AVs) rely on accurate and robust sensor observations for safety-critical decision making in a variety of conditions. The fundamental building blocks of such systems are sensors and classifiers that process ultrasound, radar, GPS, lidar, and camera signals [1]. It is of primary importance that the resulting decisions are robust to perturbations, which can take the form of different

Automated vehicular safety functions that intervene in dangerous driving situations, e.g., by emergency braking, use sensor measurements for the interpretation of the driving situation. As a consequence, they are typically very vulnerable to sensor imperfections, and unavoidable measurement errors have a negative impact on both the safety and the satisfaction of the customer, which has to be taken

Autonomous vehicles rely on their perception systems to acquire information about their immediate surroundings. It is necessary to detect the presence of other vehicles, pedestrians, and other relevant entities. Safety concerns and the need for accurate estimations have led to the introduction of lidar systems to complement camera- or radar-based perception systems. This article presents a review of

The safety and success of autonomous vehicles (AVs) depend on their ability to accurately map and respond to their surroundings in real time. One of the most promising recent technologies for depth mapping is single-photon lidar (SPL), which measures the time of flight of individual photons. The long-range capabilities (kilometers), excellent depth resolution (centimeters), and use of low-power (eye-safe)

Autonomous driving relies on a variety of sensors, especially radars, which have unique robustness under heavy rain/fog/snow and poor light conditions. With the rapid increase of the amount of radars used on modern vehicles, where most radars operate in the same frequency band, the risk of radar interference becomes a compelling issue. This article analyzes automotive radar interference and proposes

Self-driving cars constantly assess their environment to choose routes, comply with traffic regulations, and avoid hazards. To that aim, such vehicles are equipped with wireless communications transceivers as well as multiple sensors, including automotive radars. The fact that autonomous vehicles implement both radar and communications motivates designing these functionalities in a joint manner. Such

Important requirements for automotive radar are high resolution, low hardware cost, and small size. Multiple-input, multiple-output (MIMO) radar technology has been receiving considerable attention from automotive radar manufacturers because it can achieve a high angular resolution with relatively small numbers of antennas. For that ability, it has been exploited in the current-generation automotive

Artificial neural networks (ANNs) have long been used as a mathematical modeling method and have recently found numerous applications in science and technology, including computer vision, signal processing, and machine learning [1], to name a few. Although notable function approximation results exist [2], theoretical explanations have yet to catch up with newer developments, particularly with regard

Recently, an observer-based algorithm was reviewed that is able to perform recursive sliding discrete Fourier transform (SDFT) [1]. DFT is the basic algorithm used for Fourier analysis [2], but it provides unbiased estimates only if the sampling is coherent, i.e., the ratio of the sampling frequency fs and the input signal frequency fin is a rational number. Coherent sampling of real-life periodic

Prospective authors are requested to submit new, unpublished manuscripts for inclusion in the upcoming event described in this call for papers.

Presents the introductory editorial for this issue of the publication.

Distributed learning has become a critical enabler of the massively connected world that many people envision. This article discusses four key elements of scalable distributed processing and real-time intelligence: problems, data, communication, and computation. Our aim is to provide a unique perspective of how these elements should work together in an effective and coherent manner. In particular,

There is a growing cross-disciplinary effort in the broad domain of optimization and learning with streams of data, applied to settings where traditional batch optimization techniques cannot produce solutions at time scales that match the interarrival times of the data points due to computational and/or communication bottlenecks. Special types of online algorithms can handle this situation, and this

Presents the front cover for this issue of the publication.

Presents the table of contents for this issue of the publication.

Presents a listing of the editorial board, board of governors, current staff, committee members, and/or society editors for this issue of the publication.

Presents the President�s message for this issue of the publication.

Researchers worldwide are continuing to advance photo and video technologies, developing faster high-resolution cameras and taking advantage of artificial intelligence (AI), machine learning (ML), and other cutting-edge tools. As a result, novel applications are appearing in an almost endless number of fields, including scientific research, sports, public safety, and personal security.

The articles in this special section focus on machine learning from distributed, streaming media. The field of machine learning has undergone radical transformations during the last decade. These transformations, which have been fueled by our ability to collect and generate tremendous volumes of training data and leverage massive amounts of lowcost computing power, have led to an explosion in research

The problem of simultaneously learning several related tasks has received considerable attention in several domains, especially in machine learning, with the so-called multitask learning (MTL) problem, or learning to learn problem [1], [2]. MTL is an approach to inductive transfer learning (using what is learned for one problem to assist with another problem), and it helps improve generalization performance

The past decade has witnessed great progress in automatic speech recognition (ASR) due to advances in deep learning. The improvements in performance can be attributed to both improved models and large-scale training data. The key to training such models is the employment of efficient distributed learning techniques. In this article, we provide an overview of distributed training techniques for deep

Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Training in heterogeneous and potentially massive networks introduces novel challenges that require a fundamental departure from standard approaches for large-scale machine learning, distributed optimization, and privacy-preserving data

Batch training of machine learning models based on neural networks is well established, whereas, to date, streaming methods are largely based on linear models. To go beyond linear in the online setting, nonparametric methods are of interest due to their universality and ability to stably incorporate new information via convexity or Bayes's rule. Unfortunately, when applied online, nonparametric methods

Game theory is a well-established tool for studying interactions among self-interested players. Under the assumption of complete information on the game composition at each player, the focal point of game-theoretic studies has been on the Nash equilibrium (NE) in analyzing game outcomes and predicting strategic behaviors of rational players.

This article provides an overview of distributed gradient methods for solving convex machine learning problems of the form minx ∈ Rn (1/m) ∑i = 1m fi(x) in a system consisting of m agents that are embedded in a communication network. Each agent i has a collection of data captured by its privately known objective function fi(x). The distributed algorithms considered here obey two simple rules: privately

Decentralized methods to solve finite-sum minimization problems are important in many signal processing and machine learning tasks where the data samples are distributed across a network of nodes, and raw data sharing is not permitted due to privacy and/or resource constraints. In this article, we review decentralized stochastic first-order methods and provide a unified algorithmic framework that combines