在本文中，据我们所知，我们提供了将各种掩盖机制纳入变形金刚以可扩展方式融入变形金刚结构的第一种综合方法。我们表明，有关线性因果关注的最新结果（Choromanski等，2021）和对数线性RPE注意力（Luo等，2021）是这种一般机制的特殊情况。但是，通过将问题作为对未掩盖注意力的拓扑调制（基于图的）调制，我们以前获得了几个未知结果，包括有效的D维RPE掩盖和图形内掩蔽。我们利用许多数学技术，从光谱分析到动态编程和随机步行到新算法，以求解图形上的马尔可夫过程。我们提供相应的经验评估。

我们考虑在大型混合搜索空间上有效的黑箱优化问题，由高尺寸连续空间和复杂的组合空间的混合物组成。这样的例子通常在进化计算中产生，也是最近，神经发展和架构寻求强化学习（RL）政策。然而，不幸的是，以前的基于突变的方法在理论上和实际上均在高尺寸连续空间中遭受。因此，我们通过以高效的神经结构搜索（ENAS）引入的高度可扩展和直观的方式，通过组合进化策略和组合优化技术来提出ES-ZHAS，这是一个简单的联合优化过程，通过高效的神经结构搜索（ENAS）引入的一拍或超空地范式。 。通过这种相对简单的婚姻之间的两种不同的研究，我们能够通过优化混合空间以及通过边缘修剪和量化在流行的RL上优化BBOB功能以及组合神经网络架构来验证我们最佳的方法。基准。由于算法的模块化，我们还能够包含各种流行的技术，从不同的连续和组合优化器以及约束优化。

We introduce Performers, Transformer architectures which can estimate regular (softmax) full-rank-attention Transformers with provable accuracy, but using only linear (as opposed to quadratic) space and time complexity, without relying on any priors such as sparsity or low-rankness. To approximate softmax attentionkernels, Performers use a novel Fast Attention Via positive Orthogonal Random features approach (FAVOR+), which may be of independent interest for scalable kernel methods. FAVOR+ can also be used to efficiently model kernelizable attention mechanisms beyond softmax. This representational power is crucial to accurately compare softmax with other kernels for the first time on large-scale tasks, beyond the reach of regular Transformers, and investigate optimal attention-kernels. Performers are linear architectures fully compatible with regular Transformers and with strong theoretical guarantees: unbiased or nearly-unbiased estimation of the attention matrix, uniform convergence and low estimation variance. We tested Performers on a rich set of tasks stretching from pixel-prediction through text models to protein sequence modeling. We demonstrate competitive results with other examined efficient sparse and dense attention methods, showcasing effectiveness of the novel attention-learning paradigm leveraged by Performers.

Accomplishing safe and efficient driving is one of the predominant challenges in the controller design of connected automated vehicles (CAVs). It is often more convenient to address these goals separately and integrate the resulting controllers. In this study, we propose a controller integration scheme to fuse performance-based controllers and safety-oriented controllers safely for the longitudinal motion of a CAV. The resulting structure is compatible with a large class of controllers, and offers flexibility to design each controller individually without affecting the performance of the others. We implement the proposed safe integration scheme on a connected automated truck using an optimal-in-energy controller and a safety-oriented connected cruise controller. We validate the premise of the safe integration through experiments with a full-scale truck in two scenarios: a controlled experiment on a test track and a real-world experiment on a public highway. In both scenarios, we achieve energy efficient driving without violating safety.

This paper considers mixed traffic consisting of connected automated vehicles equipped with vehicle-to-everything (V2X) connectivity and human-driven vehicles. A control strategy is proposed for communicating pairs of connected automated vehicles, where the two vehicles regulate their longitudinal motion by responding to each other, and, at the same time, stabilize the human-driven traffic between them. Stability analysis is conducted to find stabilizing controllers, and simulations are used to show the efficacy of the proposed approach. The impact of the penetration of connectivity and automation on the string stability of traffic is quantified. It is shown that, even with moderate penetration, connected automated vehicle pairs executing the proposed controllers achieve significant benefits compared to when these vehicles are disconnected and controlled independently.

In this paper, we consider incorporating data associated with the sun's north and south polar field strengths to improve solar flare prediction performance using machine learning models. When used to supplement local data from active regions on the photospheric magnetic field of the sun, the polar field data provides global information to the predictor. While such global features have been previously proposed for predicting the next solar cycle's intensity, in this paper we propose using them to help classify individual solar flares. We conduct experiments using HMI data employing four different machine learning algorithms that can exploit polar field information. Additionally, we propose a novel probabilistic mixture of experts model that can simply and effectively incorporate polar field data and provide on-par prediction performance with state-of-the-art solar flare prediction algorithms such as the Recurrent Neural Network (RNN). Our experimental results indicate the usefulness of the polar field data for solar flare prediction, which can improve Heidke Skill Score (HSS2) by as much as 10.1%.

自由点变压器（FPT）已被提出为使用深神经网络的数据驱动的，非刚性点设置的注册方法。由于fpt不基于点附近或对应关系假设约束，因此可以通过根据倒角距离最大程度地减少无监督的损失来简单训练它。这使得fpt可以适应现实世界中的医学成像应用，在这些应用程序中可能无法获得地面变形，或者在仅在要对齐的点集中只有不同程度的完整性的情况下。为了测试FPT及其对培训数据集的依赖性的对应关系的限制，这项工作探讨了FPT从良好策划的非医学数据集到医学成像数据集的普遍性。首先，我们在ModelNet40数据集上训练FPT，以证明其有效性和FPT的出色注册性能，而不是基于迭代和学习的点设置注册方法。其次，我们证明了缺少数据的刚性和非刚性注册和鲁棒性的卓越性能。最后，我们通过在没有额外的训练的情况下注册了重建的脊柱和通用脊柱模型的徒手超声扫描，强调了模型网训练的FPT的有趣概括性，从而在13位患者的情况下，对地面真相曲率的平均差异为1.3度。

培训神经网络以执行3D对象检测进行自主驾驶需要大量的注释数据。但是，以足够的质量和数量获得培训数据是昂贵的，有时由于人类和传感器的限制是不可能的。因此，需要一种新的解决方案来扩展当前训练方法以克服此限制并启用准确的3D对象检测。我们对上述问题的解决方案结合了半伪标记和新颖的3D增强。为了证明所提出的方法的适用性，我们为3D对象检测设计了一个卷积神经网络，与训练数据分布相比，可以显着增加检测范围。

图形神经网络（GNNS）在许多图形挖掘任务中取得了巨大的成功，这些任务从消息传递策略中受益，该策略融合了局部结构和节点特征，从而为更好的图表表示学习。尽管GNN成功，并且与其他类型的深神经网络相似，但发现GNN容易受到图形结构和节点特征的不明显扰动。已经提出了许多对抗性攻击，以披露在不同的扰动策略下创建对抗性例子的GNN的脆弱性。但是，GNNS对成功后门攻击的脆弱性直到最近才显示。在本文中，我们披露了陷阱攻击，这是可转移的图形后门攻击。核心攻击原则是用基于扰动的触发器毒化训练数据集，这可以导致有效且可转移的后门攻击。图形的扰动触发是通过通过替代模型的基于梯度的得分矩阵在图形结构上执行扰动动作来生成的。与先前的作品相比，陷阱攻击在几种方面有所不同：i）利用替代图卷积网络（GCN）模型来生成基于黑盒的后门攻击的扰动触发器； ii）它产生了没有固定模式的样品特异性扰动触发器； iii）在使用锻造中毒训练数据集训练时，在GNN的背景下，攻击转移到了不同​​的GNN模型中。通过对四个现实世界数据集进行广泛的评估，我们证明了陷阱攻击使用四个现实世界数据集在四个不同流行的GNN中构建可转移的后门的有效性

这项工作为时间延迟系统的安全关键控制提供了一个理论框架。控制屏障功能的理论可为无延迟系统提供正式安全保证，扩展到具有状态延迟的系统。引入了控制屏障功能的概念，以实现正式的安全保证，该概念通过在无限尺寸状态空间中定义的安全集的向前不变性。所提出的框架能够在动态和安全状态下处理多个延迟和分布式延迟，并对可证明安全性的控制输入提供了仿射约束。该约束可以纳入优化问题，以合成最佳和可证明的安全控制器。该方法的适用性通过数值仿真示例证明。