Search

We consider a repeatedly played generalized Nash equilibrium game. This induces a multi-agent online learning problem with joint constraints. An important challenge in this setting is that the feasible set for each agent depends on the simultaneous moves of the other agents and, therefore, varies over time. As a consequence, the agents face time-varying constraints, which are not adversarial but rather endogenous to the system. Prior work in this setting focused on convergence to a feasible solution in the limit via integrating the constraints in the objective as a penalty function. However, no existing work can guarantee that the constraints are satisfied for all iterations while simultaneously guaranteeing convergence to a generalized Nash equilibrium. This is a problem of fundamental theoretical interest and practical relevance. In this work, we introduce a new online feasible point method. Under the assumption that limited communication between the agents is allowed, this method guarantees feasibility. We identify the class of benign generalized Nash equilibrium problems, for which the convergence of our method to the equilibrium is guaranteed. We set this class of benign generalized Nash equilibrium games in context with existing definitions and illustrate our method with examples.

This paper evaluates Few-Shot Prompting with Large Language Models for Named Entity Recognition (NER). Traditional NER systems rely on extensive labeled datasets, which are costly and time-consuming to obtain. Few-Shot Prompting or in-context learning enables models to recognize entities with minimal examples. We assess state-of-the-art models like GPT-4 in NER tasks, comparing their few-shot performance to fully supervised benchmarks. Results show that while there is a performance gap, large models excel in adapting to new entity types and domains with very limited data. We also explore the effects of prompt engineering, guided output format and context length on performance. This study underscores Few-Shot Learning's potential to reduce the need for large labeled datasets, enhancing NER scalability and accessibility., Comment: Github repo: https://github.com/GEODE-project/ner-llm

Tracking the solution of time-varying variational inequalities is an important problem with applications in game theory, optimization, and machine learning. Existing work considers time-varying games or time-varying optimization problems. For strongly convex optimization problems or strongly monotone games, these results provide tracking guarantees under the assumption that the variation of the time-varying problem is restrained, that is, problems with a sublinear solution path. In this work we extend existing results in two ways: In our first result, we provide tracking bounds for (1) variational inequalities with a sublinear solution path but not necessarily monotone functions, and (2) for periodic time-varying variational inequalities that do not necessarily have a sublinear solution path-length. Our second main contribution is an extensive study of the convergence behavior and trajectory of discrete dynamical systems of periodic time-varying VI. We show that these systems can exhibit provably chaotic behavior or can converge to the solution. Finally, we illustrate our theoretical results with experiments.

In recent years, there have been frequent incidents of foreign objects intruding into railway and Airport runways. These objects can include pedestrians, vehicles, animals, and debris. This paper introduces an improved YOLOv5 architecture incorporating FasterNet and attention mechanisms to enhance the detection of foreign objects on railways and Airport runways. This study proposes a new dataset, AARFOD (Aero and Rail Foreign Object Detection), which combines two public datasets for detecting foreign objects in aviation and railway systems.The dataset aims to improve the recognition capabilities of foreign object targets. Experimental results on this large dataset have demonstrated significant performance improvements of the proposed model over the baseline YOLOv5 model, reducing computational requirements.Improved YOLO model shows a significant improvement in precision by 1.2%, recall rate by 1.0%, and mAP@.5 by 0.6%, while mAP@.5-.95 remained unchanged. The parameters were reduced by approximately 25.12%, and GFLOPs were reduced by about 10.63%. In the ablation experiment, it is found that the FasterNet module can significantly reduce the number of parameters of the model, and the reference of the attention mechanism can slow down the performance loss caused by lightweight.

Orientation: The study explores the connections among servant leadership, burnout, and work ethic culture in organizations. It aims to provide a detailed understanding of how servant leadership influences work ethic culture, especially by considering the role of burnout. Research Purpose: This study aims to understand how servant leadership influences work ethic culture and explore the mediating role of burnout in this relationship. Motivation for the Study: This study wants to fill gaps in our understanding of how servant leadership, burnout, and work ethic culture are connected. It seeks to add useful insights to what we already know from previous research. Research Approach/Design and Method: The study, using surveys and statistics, examines the links between servant leadership, burnout, and work ethic culture in 113 hotels in Bandung, Indonesia, with 339 participants. A 183-sample, chosen with a 0.05 margin of error, underwent SEM-PLS analysis using SmartPLS 3.0. Main Findings: The key findings underscore that servant leadership exerts a positive influence on work ethic culture, and burnout plays a pivotal mediating role in this dynamic. The results shed light on the intricate dynamics shaping organizational cultures. Practical/Managerial Implications: The findings aid organizations in forming supportive leadership policies, promoting employee well-being, and fostering ethical work culture. Managers can apply these insights to enhance leadership practices and reduce burnout impact. Contribution/Value-Add: This study clarifies the connection between servant leadership, burnout, and work ethic culture. The findings offer insights for future research and practical actions in organizational leadership.

Despite the growing popularity of digital twin (DT) developments, there is a lack of common understanding and definition for important concepts of DT. It is needed to address this gap by building a shared understanding of DT before it becomes an obstacle for future work. With this challenge in view, the objective of our study is to assess the existing DT from various domains on a common basis and to unify the knowledge and understanding of DT developers and stakeholders before practice. To achieve this goal, we conducted a systematic literature review and analyzed 25 selected papers to identify and discuss the characteristics of existing DT's. The review shows an inconsistency and case-specific choices of dimensions in assessing DT. Therefore, this article proposes a four-dimensional evaluation framework to assess the maturity of digital twins across different domains, focusing on the characteristics of digital models. The four identified dimensions in this model are Capability, Cooperability, Coverage, and Lifecycle. Additionally, a weight mechanism is implemented inside the model to adapt the importance of each dimension for different application requirements. Several case studies are devised to validate the proposed model in general, industrial and scientific cases., Comment: This is a draft of the article that subject to future change and correction

We give the explicit description of the NPL-operad structure on the free commutative monoid $\mathbf E\circ \mathbf q$ generated by a given positive operad $\mathbf q$. We propose to name NPL-operad a weak form of operad in which the nested associativity axiom is weakened down to a nested pre-Lie condition. This structure is new up to our knowledge., Comment: Major correction of the previous (withdrawn) version

It has become mainstream in computer vision and other machine learning domains to reuse backbone networks pre-trained on large datasets as preprocessors. Typically, the last layer is replaced by a shallow learning machine of sorts; the newly-added classification head and (optionally) deeper layers are fine-tuned on a new task. Due to its strong performance and simplicity, a common pre-trained backbone network is ResNet152.However, ResNet152 is relatively large and induces inference latency. In many cases, a compact and efficient backbone with similar performance would be preferable over a larger, slower one. This paper investigates techniques to reuse a pre-trained backbone with the objective of creating a smaller and faster model. Starting from a large ResNet152 backbone pre-trained on ImageNet, we first reduce it from 51 blocks to 5 blocks, reducing its number of parameters and FLOPs by more than 6 times, without significant performance degradation. Then, we split the model after 3 blocks into several branches, while preserving the same number of parameters and FLOPs, to create an ensemble of sub-networks to improve performance. Our experiments on a large benchmark of $40$ image classification datasets from various domains suggest that our techniques match the performance (if not better) of ``classical backbone fine-tuning'' while achieving a smaller model size and faster inference speed.

Extensive bedside monitoring in Intensive Care Units (ICUs) has resulted in complex temporal data regarding patient physiology, which presents an upscale context for clinical data analysis. In the other hand, identifying the time-series patterns within these data may provide a high aptitude to predict clinical events. Hence, we investigate, during this work, the implementation of an automatic data-driven system, which analyzes large amounts of multivariate temporal data derived from Electronic Health Records (EHRs), and extracts high-level information so as to predict in-hospital mortality and Length of Stay (LOS) early. Practically, we investigate the applicability of LSTM network by reducing the time-frame to 6-hour so as to enhance clinical tasks. The experimental results highlight the efficiency of LSTM model with rigorous multivariate time-series measurements for building real-world prediction engines.

Non-equilibrium and active effects in mesoscopic scale systems have heralded a new era of scientific inquiries, whether concerning meta-materials or biological systems such as bacteria and cellular components. At mesoscopic scales, experimental and theoretical treatments of membranes, and other quasi-two-dimensional elastic surfaces cannot generically ignore Brownian motion and other thermal effects. In this paper we aim to study the behavior of thermally fluctuating 2-D elastic membranes possessing odd elastic moduli embedded in higher dimensions. We implement an isotropic generalization of the elastic tensor that includes odd elastic moduli, $K_{odd}$ and $A_{odd}$, that break conservation of energy and angular momentum respectively, due to cite{scheibner2020odd}. Naturally this introduces active and non-equilibrium effects. Passive equilibrium thermalized elastic membranes possess effective (renormalized) Lam\'e coefficients that reduce with increasing system size and a diverging effective bending rigidity. Introducing two odd elastic moduli means that deformations from a reference state can induce chiral forces that cannot be derived from a Hamiltonian. Thus, the behavior of odd elastic membranes must instead be investigated with Langevin equations. If fluctuation-dissipation relations hold, we calculate via the renormalization group that at long length scales, active effects due to $K_{odd}$ can be effectively ignored whereas $A_{odd}$ cannot. To validate these findings, we developed an advanced force implementation methodology, inspired by the $(T)$-scheme prevalent in vertex models. This contributed to a new method for the simulation of elastic membranes in higher dimensions, as detailed recently in \cite{matoz2020wrinkle}. The novelty of the method is that microscopic/discrete and continuum in-plane elastic moduli are one-to-one and thus no coarse-graining is needed.

We investigate the effect of thermal fluctuations on the mechanical properties of nanotubes by employing tools from statistical physics. For 2D sheets it was previously shown that thermal fluctuations effectively renormalize elastic moduli beyond a characteristic temperature-dependent thermal length scale (a few nanometers for graphene at room temperature), where the bending rigidity increases, while the in-plane elastic moduli reduce in a scale-dependent fashion with universal power law exponents. However, the curvature of nanotubes produces new phenomena. In nanotubes, competition between stretching and bending costs associated with radial fluctuations introduces a characteristic elastic length scale, which is proportional to the geometric mean of the radius and effective thickness. Beyond elastic length scale, we find that the in-plane elastic moduli stop renormalizing in the axial direction, while they continue to renormalize in the circumferential direction beyond the elastic length scale albeit with different universal exponents. The bending rigidity, however, stops renormalizing in the circumferential direction at the elastic length scale. These results were verified using molecular dynamics simulations.

In the first-order query model for zero-sum $K\times K$ matrix games, players observe the expected pay-offs for all their possible actions under the randomized action played by their opponent. This classical model has received renewed interest after the discovery by Rakhlin and Sridharan that $\epsilon$-approximate Nash equilibria can be computed efficiently from $O(\frac{\ln K}{\epsilon})$ instead of $O(\frac{\ln K}{\epsilon^2})$ queries. Surprisingly, the optimal number of such queries, as a function of both $\epsilon$ and $K$, is not known. We make progress on this question on two fronts. First, we fully characterise the query complexity of learning exact equilibria ($\epsilon=0$), by showing that they require a number of queries that is linear in $K$, which means that it is essentially as hard as querying the whole matrix, which can also be done with $K$ queries. Second, for $\epsilon > 0$, the current query complexity upper bound stands at $O(\min(\frac{\ln(K)}{\epsilon} , K))$. We argue that, unfortunately, obtaining a matching lower bound is not possible with existing techniques: we prove that no lower bound can be derived by constructing hard matrices whose entries take values in a known countable set, because such matrices can be fully identified by a single query. This rules out, for instance, reducing to an optimization problem over the hypercube by encoding it as a binary payoff matrix. We then introduce a new technique for lower bounds, which allows us to obtain lower bounds of order $\tilde\Omega(\log(\frac{1}{K\epsilon})$ for any $\epsilon \leq 1 / (cK^4)$, where $c$ is a constant independent of $K$. We further discuss possible future directions to improve on our techniques in order to close the gap with the upper bounds.

In the past few years, Differentiable Neural Architecture Search (DNAS) rapidly imposed itself as the trending approach to automate the discovery of deep neural network architectures. This rise is mainly due to the popularity of DARTS, one of the first major DNAS methods. In contrast with previous works based on Reinforcement Learning or Evolutionary Algorithms, DNAS is faster by several orders of magnitude and uses fewer computational resources. In this comprehensive survey, we focus specifically on DNAS and review recent approaches in this field. Furthermore, we propose a novel challenge-based taxonomy to classify DNAS methods. We also discuss the contributions brought to DNAS in the past few years and its impact on the global NAS field. Finally, we conclude by giving some insights into future research directions for the DNAS field., Comment: Under review at ACM Computing Surveys. 36 pages, 16 figures

Omnidirectional images, aka 360 images, can deliver immersive and interactive visual experiences. As their popularity has increased dramatically in recent years, evaluating the quality of 360 images has become a problem of interest since it provides insights for capturing, transmitting, and consuming this new media. However, directly adapting quality assessment methods proposed for standard natural images for omnidirectional data poses certain challenges. These models need to deal with very high-resolution data and implicit distortions due to the spherical form of the images. In this study, we present a method for no-reference 360 image quality assessment. Our proposed ST360IQ model extracts tangent viewports from the salient parts of the input omnidirectional image and employs a vision-transformers based module processing saliency selective patches/tokens that estimates a quality score from each viewport. Then, it aggregates these scores to give a final quality score. Our experiments on two benchmark datasets, namely OIQA and CVIQ datasets, demonstrate that as compared to the state-of-the-art, our approach predicts the quality of an omnidirectional image correlated with the human-perceived image quality. The code has been available on https://github.com/Nafiseh-Tofighi/ST360IQ, Comment: ICASSP 2023