We present AircraftVerse, a publicly available aerial vehicle design dataset. Aircraft design encompasses different physics domains and, hence, multiple modalities of representation. The evaluation of these designs requires the use of scientific analytical and simulation models ranging from computer-aided design tools for structural and manufacturing analysis, computational fluid dynamics tools for drag and lift computation, battery models for energy estimation, and simulation models for flight control and dynamics. AircraftVerse contains $27{,}714$ diverse air vehicle designs - the largest corpus of designs with this level of complexity. Each design comprises the following artifacts: a symbolic design tree describing topology, propulsion subsystem, battery subsystem, and other design details; a STandard for the Exchange of Product (STEP) model data; a 3D CAD design using a stereolithography (STL) file format; a 3D point cloud for the shape of the design; and evaluation results from high fidelity state-of-the-art physics models that characterize performance metrics such as maximum flight distance and hover-time. We also present baseline surrogate models that use different modalities of design representation to predict design performance metrics, which we provide as part of our dataset release. Finally, we discuss the potential impact of this dataset on the use of learning in aircraft design, and more generally, in the emerging field of deep learning for scientific design. AircraftVerse is accompanied by a datasheet as suggested in the recent literature, and it is released under Creative Commons Attribution-ShareAlike (CC BY-SA) license. The dataset with baseline models are hosted at http://doi.org/10.5281/zenodo.6525446, code at https://github.com/SRI-CSL/AircraftVerse, and the dataset description at https://uavdesignverse.onrender.com/.

Gradient-descent (GD) based algorithms are an indispensable tool for optimizing modern machine learning models. The paper considers distributed stochastic GD (D-SGD)--a network-based variant of GD. Distributed algorithms play an important role in large-scale machine learning problems as well as the Internet of Things (IoT) and related applications. The paper considers two main issues. First, we study convergence of D-SGD to critical points when the loss function is nonconvex and nonsmooth. We consider a broad range of nonsmooth loss functions including those of practical interest in modern deep learning. It is shown that, for each fixed initialization, D-SGD converges to critical points of the loss with probability one. Next, we consider the problem of avoiding saddle points. It is well known that classical GD avoids saddle points; however, analogous results have been absent for distributed variants of GD. For this problem, we again assume that loss functions may be nonconvex and nonsmooth, but are smooth in a neighborhood of a saddle point. It is shown that, for any fixed initialization, D-SGD avoids such saddle points with probability one. Results are proved by studying the underlying (distributed) gradient flow, using the ordinary differential equation (ODE) method of stochastic approximation.

The paper considers the problem of network-based computation of global minima in smooth nonconvex optimization problems. It is known that distributed gradient-descent-type algorithms can achieve convergence to the set of global minima by adding slowly decaying Gaussian noise in order to escape local minima. However, the technical assumptions under which convergence is known to occur can be restrictive in practice. In particular, in known convergence results, the local objective functions possessed by agents are required to satisfy a highly restrictive bounded-gradient-dissimilarity condition. The paper demonstrates convergence to the set of global minima while relaxing this key assumption.

Mobile crowd sensing (MCS) has been used to enable a wide range of resource-discovery applications by exploiting the "wisdom" of many mobile users. However, in many applications, a user's valuation depends on other users' sensory data, which introduces the problem of interdependent valuations. This feature can encourage sensory data misreport, hence makes economic mechanisms challenging. While some work has been done to address this problem, the issues of private utility information and communication overheads remain unsolved. In this study, we formulate the first interdependent-valuation model for the resource-discovery MCS systems, aiming to elicit truthful sensory reports and utility information and to maximize expected social welfare. We design a Truthful Sense-And-Bid (T-SAB) Mechanism based on surrogate functions, which can reveal marginal utility information by only requiring each user to submit one-dimensional signaling per resource. We show that the surrogate function and a reward function can limit users' willingness to misreport, when users have small informational sizes, a reasonable condition in large-scale MCS systems. Consequently, our T-SAB Mechanism yields a Perfect Bayesian Equilibrium (PBE) with the efficient allocation outcome, approximate truthfulness, individual rationality, and approximate budget balance. To illustrate the effectiveness of the T-SAB Mechanism, we perform a case study of a cognitive radio network. We demonstrate that the social welfare gain of the T-SAB Mechanism can achieve up to 20% social welfare gain comparing with a benchmark.

This paper introduces a novel design of phase locked loop (PLL) based oscillatory neural networks (ONNs) to mitigate the frequency clustering phenomenon caused by transmission delays in real systems. Theoretical analysis of the ONN reveals that transmission delays can produce frequency clustering that leads to synchronization and convergence failure. This paper describes the redesign of ONN dynamics and associated system-level architecture to achieve robustness. Specifically, we first demonstrate that using the phase information of zero-crossing points of inputs as the PLL error signal enables the ONN dynamical model to correctly synchronize under uniform transmission delays. A Type-II PLL based ONN architecture is shown via simulation to provide this property in hardware. Furthermore, to accommodate non-uniform transmission delays in hardware, a phase synchronization technique is proposed that is shown to provide the correct synchronization behavior.