Nonnegative matrix factorization (NMF) often relies on the separability condition for tractable algorithm design. Separability-based NMF is mainly handled by two types of approaches, namely, greedy pursuit and convex programming. A notable convex NMF formulation is the so-called self-dictionary multiple measurement vectors (SD-MMV), which can work without knowing the matrix rank a priori, and is arguably more resilient to error propagation relative to greedy pursuit. However, convex SD-MMV renders a large memory cost that scales quadratically with the problem size. This memory challenge has been around for a decade, and a major obstacle for applying convex SD-MMV to big data analytics. This work proposes a memory-efficient algorithm for convex SD-MMV. Our algorithm capitalizes on the special update rules of a classic algorithm from the 1950s, namely, the Frank-Wolfe (FW) algorithm. It is shown that, under reasonable conditions, the FW algorithm solves the noisy SD-MMV problem with a memory cost that grows linearly with the amount of data. To handle noisier scenarios, a smoothed group sparsity regularizer is proposed to improve robustness while maintaining the low memory footprint with guarantees. The proposed approach presents the first linear memory complexity algorithmic framework for convex SD-MMV based NMF. The method is tested over a couple of unsupervised learning tasks, i.e., text mining and community detection, to showcase its effectiveness and memory efficiency.

This paper develops a novel unsupervised algorithm for belief representation learning in polarized networks that (i) uncovers the latent dimensions of the underlying belief space and (ii) jointly embeds users and content items (that they interact with) into that space in a manner that facilitates a number of downstream tasks, such as stance detection, stance prediction, and ideology mapping. Inspired by total correlation in information theory, we propose the Information-Theoretic Variational Graph Auto-Encoder (InfoVGAE) that learns to project both users and content items (e.g., posts that represent user views) into an appropriate disentangled latent space. To better disentangle latent variables in that space, we develop a total correlation regularization module, a Proportional-Integral (PI) control module, and adopt rectified Gaussian distribution to ensure the orthogonality. The latent representation of users and content can then be used to quantify their ideological leaning and detect/predict their stances on issues. We evaluate the performance of the proposed InfoVGAE on three real-world datasets, of which two are collected from Twitter and one from U.S. Congress voting records. The evaluation results show that our model outperforms state-of-the-art unsupervised models by reducing 10.5% user clustering errors and achieving 12.1% higher F1 scores for stance separation of content items. In addition, InfoVGAE produces a comparable result with supervised models. We also discuss its performance on stance prediction and user ranking within ideological groups.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. Ukraine's defense ministry on Saturday claimed it had sunk a Russian Serna-class landing boat off of the now-famous Snake Island which has stood as a symbol of resistance since the beginning of the war. Undated video footage posted to social media appears to show an airstrike hitting a landing vessel that had soldiers on board. Spokesman for the Odesa Regional Military Administration, Serhii Bratchuk, told Ukrainian news outlet Pravda that Zmiinyi Island – also known as Snake Island – has become "a symbol of our rock-hard endurance and our ability to shatter the enemy's most persistent efforts."

In the snowy streets of the north Ukrainian town of Trostyanets, the Russian missile system fires rockets every second. Tanks and military vehicles are parked on either side of the blasting artillery system, positioned among houses and near the town's railway system. The weapon is not working alone, though. Hovering tens of meters above it and recording the assault is a Ukrainian drone. The drone isn't a sophisticated military system, but a small, commercial machine that anyone can buy.

There has been no better time to be in the world of artificial intelligence than now. AI has achieved an inflection point and is poised to transform every industry. Much has already been written about specific applications of AI. In this article, I take a step back to consider how artificial intelligence is poised to fundamentally restructure broader swaths of our economy and society over the next decade with five bold predictions that are informed by my expertise and immersion in the field. Important science--think large-scale clinical trials or building particle colliders--is expensive and time-consuming.

Secretary shall support a program of fundamental research, development, and demonstration of energy efficient computing and data center technologies relevant to advanced computing applications, including high performance computing, artificial intelligence, and scientific machine learning.").

Nowcasting can play a key role in giving policymakers timelier insight to data published with a significant time lag, such as final GDP figures. Currently, there are a plethora of methodologies and approaches for practitioners to choose from. However, there lacks a comprehensive comparison of these disparate approaches in terms of predictive performance and characteristics. This paper addresses that deficiency by examining the performance of 12 different methodologies in nowcasting US quarterly GDP growth, including all the methods most commonly employed in nowcasting, as well as some of the most popular traditional machine learning approaches. Performance was assessed on three different tumultuous periods in US economic history: the early 1980s recession, the 2008 financial crisis, and the COVID crisis. The two best performing methodologies in the analysis were long short-term memory artificial neural networks (LSTM) and Bayesian vector autoregression (BVAR).

Development and optimization of biopharmaceutical production processes with cell cultures is cost- and time-consuming and often performed rather empirically. Efficient optimization of multiple-objectives like process time, viable cell density, number of operating steps & cultivation scales, required medium, amount of product as well as product quality depicts a promising approach. This contribution presents a workflow which couples uncertainty-based upstream simulation and Bayes optimization using Gaussian processes. Its application is demonstrated in a simulation case study for a relevant industrial task in process development, the design of a robust cell culture expansion process (seed train), meaning that despite uncertainties and variabilities concerning cell growth, low variations of viable cell density during the seed train are obtained. Compared to a non-optimized reference seed train, the optimized process showed much lower deviation rates regarding viable cell densities (<~10% instead of 41.7%) using 5 or 4 shake flask scales and seed train duration could be reduced by 56 h from 576 h to 520 h. Overall, it is shown that applying Bayes optimization allows for optimization of a multi-objective optimization function with several optimizable input variables and under a considerable amount of constraints with a low computational effort. This approach provides the potential to be used in form of a decision tool, e.g. for the choice of an optimal and robust seed train design or for further optimization tasks within process development.

Channel estimation is a critical task in intelligent reflecting surface (IRS)-assisted wireless systems due to the uncertainties imposed by environment dynamics and rapid changes in the IRS configuration. To deal with these uncertainties, deep learning (DL) approaches have been proposed. Previous works consider centralized learning (CL) approach for model training, which entails the collection of the whole training dataset from the users at the base station (BS), hence introducing huge transmission overhead for data collection. To address this challenge, this paper proposes a federated learning (FL) framework to jointly estimate both direct and cascaded channels in IRS-assisted wireless systems. We design a single convolutional neural network trained on the local datasets of the users without sending them to the BS. We show that the proposed FL-based channel estimation approach requires approximately 60% fewer pilot signals and it exhibits 12 times lower transmission overhead than CL, while maintaining satisfactory performance close to CL. In addition, it provides lower estimation error than the state-of-the-art DL-based schemes.

This survey article assesses and compares existing critiques of current fairness-enhancing technical interventions in machine learning (ML) that draw from a range of non-computing disciplines, including philosophy, feminist studies, critical race and ethnic studies, legal studies, anthropology, and science and technology studies. It bridges epistemic divides in order to offer an interdisciplinary understanding of the possibilities and limits of hegemonic computational approaches to ML fairness for producing just outcomes for society's most marginalized. The article is organized according to nine major themes of critique wherein these different fields intersect: 1) how "fairness" in AI fairness research gets defined; 2) how problems for AI systems to address get formulated; 3) the impacts of abstraction on how AI tools function and its propensity to lead to technological solutionism; 4) how racial classification operates within AI fairness research; 5) the use of AI fairness measures to avoid regulation and engage in ethics washing; 6) an absence of participatory design and democratic deliberation in AI fairness considerations; 7) data collection practices that entrench "bias," are non-consensual, and lack transparency; 8) the predatory inclusion of marginalized groups into AI systems; and 9) a lack of engagement with AI's long-term social and ethical outcomes. Drawing from these critiques, the article concludes by imagining future ML fairness research directions that actively disrupt entrenched power dynamics and structural injustices in society.