Point Bridge Capital CEO Hal Lambert says Elon Musk is the Thomas Edison of our generation. SpaceX founder Elon Musk expects unmanned drones will outlive fighter jets in the U.S. Air Force. "It's not [that] I want the future to be this," the billionaire entrepreneur added during a fireside chat about the future of air defense with Gen. Jay Raymond, chief of space operations for the Space Force, at the 2020 Air Warfare Symposium on Friday. "The fighter jet era has passed." The founder of electric-car maker Tesla re-emphasized the point on Twitter when a platform user brought up his statement that the new Lockheed Martin F-35 Joint Strike Fighter should have a competitor.

This model was designed to look for chemical features that make molecules effective at killing E.coli in a process that involved training on 2,500 molecules including 1,700 FDA approved drugs and a set of 800 natural products with diverse structures and a range of bioactivities. Once trained it was tested on a library of 6,000 compounds, and the model picked out one molecule predicted to have strong antibacterial activity and chemical structure different from any existing antibiotics. Then using a different machine deep learning algorithm model the newly identified Halicin molecule was shown to likely have low toxicity to human cells.

Crowdsourcing is a popular methodology to collect manual labels at scale. Such labels are often used to train AI models and, thus, quality control is a key aspect in the process. One of the most popular quality assurance mechanisms in paid micro-task crowdsourcing is based on gold questions: the use of a small set of tasks of which the requester knows the correct answer and, thus, is able to directly assess crowd work quality. In this paper, we show that such mechanism is prone to an attack carried out by a group of colluding crowd workers that is easy to implement and deploy: the inherent size limit of the gold set can be exploited by building an inferential system to detect which parts of the job are more likely to be gold questions. The described attack is robust to various forms of randomisation and programmatic generation of gold questions. We present the architecture of the proposed system, composed of a browser plug-in and an external server used to share information, and briefly introduce its potential evolution to a decentralised implementation. We implement and experimentally validate the gold detection system, using real-world data from a popular crowdsourcing platform.  Our experimental results show that crowdworkers using the proposed system spend more time on signalled gold questions but do not neglect the others thus achieving an increased overall work quality. Finally, we discuss the economic and sociological implications of this kind of attack.

Decades of global research and development initiatives such as Integrated Computational Materials Engineering (ICME) [2][3] and the Materials Genome Initiative (MGI) [4] have demonstrated the ability for both physics-based and data-driven computations to accelerate the discovery and deployment of new alloys. It is established that machine learning (ML) can model process-structure-property relationships of alloys [5][6]. Of equal or greater impact, ML can greatly reduce the number of physics-based experiments and calculations needed to discover and design new materials with optimal properties [7][8][9]. However, the robust prediction of a new alloy and its processing designed to meet a desired, yet not previously achieved performance remains an open challenge; one that is met in this work. In other sects of materials science and engineering where new materials have been successfully predicted, the formulation of effective data descriptors, or "feature engineering," has emerged as a critical data pre-processing step to enable better performances from ML. Most such studies have focused on using high-throughput physics-based calculations together with chemical element descriptors to assist ML prediction [7][9].

This paper attempts to answer the question whether neural network pruning can be used as a tool to achieve differential privacy without losing much data utility. As a first step towards understanding the relationship between neural network pruning and differential privacy, this paper proves that pruning a given layer of the neural network is equivalent to adding a certain amount of differentially private noise to its hidden-layer activations. The paper also presents experimental results to show the practical implications of the theoretical finding and the key parameter values in a simple practical setting. These results show that neural network pruning can be a more effective alternative to adding differentially private noise for neural networks.

We consider the problem of simultaneous estimation of a sequence of dependent parameters that are generated from a hidden Markov model. Based on observing a noise contaminated vector of observations from such a sequence model, we consider simultaneous estimation of all the parameters irrespective of their hidden states under square error loss. We study the roles of statistical shrinkage for improved estimation of these dependent parameters. Being completely agnostic on the distributional properties of the unknown underlying Hidden Markov model, we develop a novel non-parametric shrinkage algorithm. Our proposed method elegantly combines \textit{Tweedie}-based non-parametric shrinkage ideas with efficient estimation of the hidden states under Markovian dependence. Based on extensive numerical experiments, we establish superior performance our our proposed algorithm compared to non-shrinkage based state-of-the-art parametric as well as non-parametric algorithms used in hidden Markov models. We provide decision theoretic properties of our methodology and exhibit its enhanced efficacy over popular shrinkage methods built under independence. We demonstrate the application of our methodology on real-world datasets for analyzing of temporally dependent social and economic indicators such as search trends and unemployment rates as well as estimating spatially dependent Copy Number Variations.

Thompson sampling is one of the most widely used algorithms for many online decision problems, due to its simplicity in implementation and superior empirical performance over other state-of-the-art methods. Despite its popularity and empirical success, it has remained an open problem whether Thompson sampling can achieve the minimax optimal regret $O(\sqrt{KT})$ for $K$-armed bandit problems, where $T$ is the total time horizon. In this paper, we solve this long open problem by proposing a new Thompson sampling algorithm called MOTS that adaptively truncates the sampling result of the chosen arm at each time step. We prove that this simple variant of Thompson sampling achieves the minimax optimal regret bound $O(\sqrt{KT})$ for finite time horizon $T$ and also the asymptotic optimal regret bound when $T$ grows to infinity as well. This is the first time that the minimax optimality of multi-armed bandit problems has been attained by Thompson sampling type of algorithms.

In a large number of fields such as biomedical signal processing, speech and acoustics and climate science, data consists of a high number of simultaneous or sequential measurements of different aspects of the same phenomenon. Such data is inherently high dimensional, however it contains strong within-observation correlations and smoothness patterns which can be utilized in the learning process. A possible way to do so is to represent those observations as functions rather than vectors, opening the door to Functional Data Analysis (FDA) Ramsay & Silverman (2005), a research area that has recently attracted a growing interest due to the ubiquity of embedded devices and sensor data. In practice, FDA relies on the assumption that the sampling rate at which data are collected is high enough to get functional observations. Of special interest is the general problem of functional-output regression in which the output variable to regress is a function and no specific assumption is made on the input variable that can can be of any type, including functions. While functional linear model have received a great deal of attention--see Ramsay & Silverman (2005), Morris (2015) and references therein--nonlinear ones have been less studied.

Deep neural networks (DNNs) have achieved significant performance in various tasks. However, recent studies have shown that DNNs can be easily fooled by small perturbation on the input, called adversarial attacks. As the extensions of DNNs to graphs, Graph Neural Networks (GNNs) have been demonstrated to inherit this vulnerability. Adversary can mislead GNNs to give wrong predictions by modifying the graph structure such as manipulating a few edges. This vulnerability has arisen tremendous concerns for adapting GNNs in safety-critical applications and has attracted increasing research attention in recent years. Thus, it is necessary and timely to provide a comprehensive overview of existing graph adversarial attacks and the countermeasures. In this survey, we categorize existing attacks and defenses, and review the corresponding state-of-the-art methods. Furthermore, we have developed a repository with representative algorithms (https://github.com/DSE-MSU/DeepRobust/tree/master/deeprobust/graph). The repository enables us to conduct empirical studies to deepen our understandings on attacks and defenses on graphs.

Several recent works have found the emergence of grounded compositional language in the communication protocols developed by mostly cooperative multi-agent systems when learned end-to-end to maximize performance on a downstream task. However, human populations learn to solve complex tasks involving communicative behaviors not only in fully cooperative settings but also in scenarios where competition acts as an additional external pressure for improvement. In this work, we investigate whether competition for performance from an external, similar agent team could act as a social influence that encourages multi-agent populations to develop better communication protocols for improved performance, compositionality, and convergence speed. We start from Task & Talk, a previously proposed referential game between two cooperative agents as our testbed and extend it into Task, Talk & Compete, a game involving two competitive teams each consisting of two aforementioned cooperative agents. Using this new setting, we provide an empirical study demonstrating the impact of competitive influence on multi-agent teams. Our results show that an external competitive influence leads to improved accuracy and generalization, as well as faster emergence of communicative languages that are more informative and compositional.