We propose urgency programs, a new programming model with support for alternation, imperfect information, and recursion. The novelty are urgency annotations that decorate the (angelic and demonic) choice operators and control the order in which alternation is resolved. We study standard notions of contextual equivalence for urgency programs. Our first main result are fully abstract characterizations of these relations based on sound and complete axiomatizations. Our second main result settles their computability via a normal form construction. Notably, we show that the contextual preorder is (2h-1)-EXPTIME-complete for programs of maximal urgency h when the regular observable is given as an input resp. PTIME-complete when the regular observable is fixed. We designed urgency programs as a framework in which it is convenient to formulate and study verification and synthesis problems. We demonstrate this on a number of examples including the verification of concurrent and recursive programs and hyper model checking.
相關內容
When optimizing problems with uncertain parameter values in a linear objective, decision-focused learning enables end-to-end learning of these values. We are interested in a stochastic scheduling problem, in which processing times are uncertain, which brings uncertain values in the constraints, and thus repair of an initial schedule may be needed. Historical realizations of the stochastic processing times are available. We show how existing decision-focused learning techniques based on stochastic smoothing can be adapted to this scheduling problem. We include an extensive experimental evaluation to investigate in which situations decision-focused learning outperforms the state of the art for such situations: scenario-based stochastic optimization.
Adversarial training integrates adversarial examples during model training to enhance robustness. However, its application in fixed dataset settings differs from real-world dynamics, where data accumulates incrementally. In this study, we investigate Adversarially Robust Class Incremental Learning (ARCIL), a method that combines adversarial robustness with incremental learning. We observe that combining incremental learning with naive adversarial training easily leads to a loss of robustness. We discover that this is attributed to the disappearance of the flatness of the loss function, a characteristic of adversarial training. To address this issue, we propose the Flatness Preserving Distillation (FPD) loss that leverages the output difference between adversarial and clean examples. Additionally, we introduce the Logit Adjustment Distillation (LAD) loss, which adapts the model's knowledge to perform well on new tasks. Experimental results demonstrate the superiority of our method over approaches that apply adversarial training to existing incremental learning methods, which provides a strong baseline for incremental learning on adversarial robustness in the future. Our method achieves AutoAttack accuracy that is 5.99\%p, 5.27\%p, and 3.90\%p higher on average than the baseline on split CIFAR-10, CIFAR-100, and Tiny ImageNet, respectively. The code will be made available.
The increased connectivity and potential insider threats make traditional network defense vulnerable. Instead of assuming that everything behind the security perimeter is safe, the zero-trust security model verifies every incoming request before granting access. This chapter draws attention to the cyber resilience within the zero-trust model. We introduce the evolution from traditional perimeter-based security to zero trust and discuss their difference. Two key elements of the zero-trust engine are trust evaluation (TE) and policy engine (PE). We introduce the design of the two components and discuss how their interplay would contribute to cyber resilience. Dynamic game theory and learning are applied as quantitative approaches to achieve automated zero-trust cyber resilience. Several case studies and implementations are introduced to illustrate the benefits of such a security model.
Visual Programming (VP) has emerged as a powerful framework for Visual Question Answering (VQA). By generating and executing bespoke code for each question, these methods demonstrate impressive compositional and reasoning capabilities, especially in few-shot and zero-shot scenarios. However, existing VP methods generate all code in a single function, resulting in code that is suboptimal in terms of both accuracy and interpretability. Inspired by human coding practices, we propose Recursive Visual Programming (RVP), which simplifies generated routines, provides more efficient problem solving, and can manage more complex data structures. RVP is inspired by human coding practices and approaches VQA tasks with an iterative recursive code generation approach, allowing decomposition of complicated problems into smaller parts. Notably, RVP is capable of dynamic type assignment, i.e., as the system recursively generates a new piece of code, it autonomously determines the appropriate return type and crafts the requisite code to generate that output. We show RVP's efficacy through extensive experiments on benchmarks including VSR, COVR, GQA, and NextQA, underscoring the value of adopting human-like recursive and modular programming techniques for solving VQA tasks through coding.
The goal of anomaly detection is to identify observations generated by a process that is different from a reference one. An accurate anomaly detector must ensure low false positive and false negative rates. However in the online context such a constraint remains highly challenging due to the usual lack of control of the False Discovery Rate (FDR). In particular the online framework makes it impossible to use classical multiple testing approaches such as the Benjamini-Hochberg (BH) procedure. Our strategy overcomes this difficulty by exploiting a local control of the ``modified FDR'' (mFDR). An important ingredient in this control is the cardinality of the calibration set used for computing empirical $p$-values, which turns out to be an influential parameter. It results a new strategy for tuning this parameter, which yields the desired FDR control over the whole time series. The statistical performance of this strategy is analyzed by theoretical guarantees and its practical behavior is assessed by simulation experiments which support our conclusions.
Evaluating quantum circuits is currently very noisy. Therefore, developing classical bootstraps that help minimize the number of times quantum circuits have to be executed on noisy quantum devices is a powerful technique for improving the practicality of Variational Quantum Algorithms. CAFQA is a previously proposed classical bootstrap for VQAs that uses an initial ansatz that reduces to Clifford operators. CAFQA has been shown to produce fairly accurate initialization for VQA applied to molecular chemistry Hamiltonians. Motivated by this result, in this paper we seek to analyze the Clifford states that optimize the cost function for a new type of Hamiltonian, namely Transverse Field Ising Hamiltonians. Our primary result connects the problem of finding the optimal CAFQA initialization to a submodular minimization problem which in turn can be solved in polynomial time.
Innovative foundation models, such as GPT-4 and stable diffusion models, have made a paradigm shift in the realm of artificial intelligence (AI) towards generative AI-based systems. AI and machine learning (AI/ML) algorithms are envisioned to be pervasively incorporated into the future wireless communications systems. In this article, we outline the applications of diffusion models in wireless communication systems, which are a new family of probabilistic generative models that have showcased state-of-the-art performance. The key idea is to decompose data generation process over "denoising" steps, gradually generating samples out of noise. Based on two case studies presented, we show how diffusion models can be employed for the development of resilient AI-native communication systems. Specifically, we propose denoising diffusion probabilistic models (DDPM) for a wireless communication scheme with non-ideal transceivers, where 30% improvement is achieved in terms of bit error rate. In the other example, DDPM is employed at the transmitter to shape the constellation symbols, highlighting a robust out-of-distribution performance.
Data augmentation has been widely used to improve generalizability of machine learning models. However, comparatively little work studies data augmentation for graphs. This is largely due to the complex, non-Euclidean structure of graphs, which limits possible manipulation operations. Augmentation operations commonly used in vision and language have no analogs for graphs. Our work studies graph data augmentation for graph neural networks (GNNs) in the context of improving semi-supervised node-classification. We discuss practical and theoretical motivations, considerations and strategies for graph data augmentation. Our work shows that neural edge predictors can effectively encode class-homophilic structure to promote intra-class edges and demote inter-class edges in given graph structure, and our main contribution introduces the GAug graph data augmentation framework, which leverages these insights to improve performance in GNN-based node classification via edge prediction. Extensive experiments on multiple benchmarks show that augmentation via GAug improves performance across GNN architectures and datasets.
We present a new method to learn video representations from large-scale unlabeled video data. Ideally, this representation will be generic and transferable, directly usable for new tasks such as action recognition and zero or few-shot learning. We formulate unsupervised representation learning as a multi-modal, multi-task learning problem, where the representations are shared across different modalities via distillation. Further, we introduce the concept of loss function evolution by using an evolutionary search algorithm to automatically find optimal combination of loss functions capturing many (self-supervised) tasks and modalities. Thirdly, we propose an unsupervised representation evaluation metric using distribution matching to a large unlabeled dataset as a prior constraint, based on Zipf's law. This unsupervised constraint, which is not guided by any labeling, produces similar results to weakly-supervised, task-specific ones. The proposed unsupervised representation learning results in a single RGB network and outperforms previous methods. Notably, it is also more effective than several label-based methods (e.g., ImageNet), with the exception of large, fully labeled video datasets.
Benefit from the quick development of deep learning techniques, salient object detection has achieved remarkable progresses recently. However, there still exists following two major challenges that hinder its application in embedded devices, low resolution output and heavy model weight. To this end, this paper presents an accurate yet compact deep network for efficient salient object detection. More specifically, given a coarse saliency prediction in the deepest layer, we first employ residual learning to learn side-output residual features for saliency refinement, which can be achieved with very limited convolutional parameters while keep accuracy. Secondly, we further propose reverse attention to guide such side-output residual learning in a top-down manner. By erasing the current predicted salient regions from side-output features, the network can eventually explore the missing object parts and details which results in high resolution and accuracy. Experiments on six benchmark datasets demonstrate that the proposed approach compares favorably against state-of-the-art methods, and with advantages in terms of simplicity, efficiency (45 FPS) and model size (81 MB).
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191