尽管在构建强大的神经网络方面具有明显的计算优势，但使用单步方法的对抗训练（AT）是不稳定的，因为它遭受了灾难性的过度拟合（CO）：网络在对抗性训练的第一阶段获得了非平凡的鲁棒性，但突然达到了一个阶段在几次迭代中，他们很快失去了所有鲁棒性。尽管有些作品成功地预防了CO，但导致这种显着失败模式的不同机制仍然很少理解。但是，在这项工作中，我们发现数据结构与AT动力学之间的相互作用在CO中起着基本作用。特别是，通过对自然图像的典型数据集进行主动干预，我们建立了一个因果关系。在方法上单步中的数据和CO的发作。这种新的观点提供了对导致CO的机制的重要见解，并为更好地理解强大模型构建的一般动态铺平了道路。可以在https://github.com/gortizji/co_features上找到复制本文实验的代码。

尽管对图像分类任务的表现令人印象深刻，但深网络仍然难以概括其数据的许多常见损坏。为解决此漏洞，事先作品主要专注于提高其培训管道的复杂性，以多样性的名义结合多种方法。然而，在这项工作中，我们逐步回来并遵循原则的方法来实现共同腐败的稳健性。我们提出了一个普遍的数据增强方案，包括最大熵图像变换的简单系列。我们展示了Prime优于现有技术的腐败鲁棒性，而其简单和即插即用性质使其能够与其他方法结合以进一步提升其稳健性。此外，我们分析了对综合腐败图像混合策略的重要性，并揭示了在共同腐败背景下产生的鲁棒性准确性权衡的重要性。最后，我们表明我们的方法的计算效率允许它在线和离线数据增强方案轻松使用。

通过新的设计推动，允许规避光谱偏差，隐式神经表示（INRS）最近被出现为具有古典离散化表示的有希望的替代方案。尽管如此，尽管他们的实际成功，我们仍然缺乏inrs代表信号的正确理论表征。在这项工作中，我们的目标是填补这一差距，我们提出了一种在理论上分析inrs的新颖统一视角。利用谐波分析和深度学习理论的结果，我们表明大多数INR系列类似于结构化信号词典，其原子是初始映射频率集的整数谐波。该结构允许INR使用只有许多只能与深度线性增长的参数表达频率支持的信号。之后，我们探讨了初步结果关于经验神经切线内核（NTK）的近期结果的归纳偏见。具体地，我们表明NTK的特征功能可以被视为其内部产品与目标信号的内部产品确定其重建的最终性能。在这方面，我们揭示了Meta学习初始化具有类似于字典学习的NTK的重塑效果，构建字典原子作为在Meta训练期间看到的例子的组合。我们的业绩允许设计和调整小说INR架构，但对更广泛的深度学习理论界也可能感兴趣。

Optimal Power Flow (OPF) is a very traditional research area within the power systems field that seeks for the optimal operation point of electric power plants, and which needs to be solved every few minutes in real-world scenarios. However, due to the nonconvexities that arise in power generation systems, there is not yet a fast, robust solution technique for the full Alternating Current Optimal Power Flow (ACOPF). In the last decades, power grids have evolved into a typical dynamic, non-linear and large-scale control system, known as the power system, so searching for better and faster ACOPF solutions is becoming crucial. Appearance of Graph Neural Networks (GNN) has allowed the natural use of Machine Learning (ML) algorithms on graph data, such as power networks. On the other hand, Deep Reinforcement Learning (DRL) is known for its powerful capability to solve complex decision-making problems. Although solutions that use these two methods separately are beginning to appear in the literature, none has yet combined the advantages of both. We propose a novel architecture based on the Proximal Policy Optimization algorithm with Graph Neural Networks to solve the Optimal Power Flow. The objective is to design an architecture that learns how to solve the optimization problem and that is at the same time able to generalize to unseen scenarios. We compare our solution with the DCOPF in terms of cost after having trained our DRL agent on IEEE 30 bus system and then computing the OPF on that base network with topology changes

Event cameras are novel bio-inspired sensors that offer advantages over traditional cameras (low latency, high dynamic range, low power, etc.). Optical flow estimation methods that work on packets of events trade off speed for accuracy, while event-by-event (incremental) methods have strong assumptions and have not been tested on common benchmarks that quantify progress in the field. Towards applications on resource-constrained devices, it is important to develop optical flow algorithms that are fast, light-weight and accurate. This work leverages insights from neuroscience, and proposes a novel optical flow estimation scheme based on triplet matching. The experiments on publicly available benchmarks demonstrate its capability to handle complex scenes with comparable results as prior packet-based algorithms. In addition, the proposed method achieves the fastest execution time (> 10 kHz) on standard CPUs as it requires only three events in estimation. We hope that our research opens the door to real-time, incremental motion estimation methods and applications in real-world scenarios.

Neural Radiance Fields (NeRFs) are emerging as a ubiquitous scene representation that allows for novel view synthesis. Increasingly, NeRFs will be shareable with other people. Before sharing a NeRF, though, it might be desirable to remove personal information or unsightly objects. Such removal is not easily achieved with the current NeRF editing frameworks. We propose a framework to remove objects from a NeRF representation created from an RGB-D sequence. Our NeRF inpainting method leverages recent work in 2D image inpainting and is guided by a user-provided mask. Our algorithm is underpinned by a confidence based view selection procedure. It chooses which of the individual 2D inpainted images to use in the creation of the NeRF, so that the resulting inpainted NeRF is 3D consistent. We show that our method for NeRF editing is effective for synthesizing plausible inpaintings in a multi-view coherent manner. We validate our approach using a new and still-challenging dataset for the task of NeRF inpainting.

Event cameras are emerging vision sensors and their advantages are suitable for various applications such as autonomous robots. Contrast maximization (CMax), which provides state-of-the-art accuracy on motion estimation using events, may suffer from an overfitting problem called event collapse. Prior works are computationally expensive or cannot alleviate the overfitting, which undermines the benefits of the CMax framework. We propose a novel, computationally efficient regularizer based on geometric principles to mitigate event collapse. The experiments show that the proposed regularizer achieves state-of-the-art accuracy results, while its reduced computational complexity makes it two to four times faster than previous approaches. To the best of our knowledge, our regularizer is the only effective solution for event collapse without trading off runtime. We hope our work opens the door for future applications that unlocks the advantages of event cameras.

Deep Reinforcement Learning (RL) agents are susceptible to adversarial noise in their observations that can mislead their policies and decrease their performance. However, an adversary may be interested not only in decreasing the reward, but also in modifying specific temporal logic properties of the policy. This paper presents a metric that measures the exact impact of adversarial attacks against such properties. We use this metric to craft optimal adversarial attacks. Furthermore, we introduce a model checking method that allows us to verify the robustness of RL policies against adversarial attacks. Our empirical analysis confirms (1) the quality of our metric to craft adversarial attacks against temporal logic properties, and (2) that we are able to concisely assess a system's robustness against attacks.

成功培训端到端的深网进行真实运动去缩合，需要尖锐/模糊的图像对数据集，这些数据集现实且多样化，足以实现概括以实现真实的图像。获得此类数据集仍然是一项具有挑战性的任务。在本文中，我们首先回顾了现有的Deblurring基准数据集的局限性，从泛化到野外模糊图像的角度。其次，我们提出了一种有效的程序方法，以基于一个简单而有效的图像形成模型来生成清晰/模糊的图像对。这允许生成几乎无限的现实和多样化的培训对。我们通过在模拟对上训练现有的DeBlurring架构，并在四个真实模糊图像的标准数据集中对其进行评估，从而证明了所提出的数据集的有效性。我们观察到使用建议方法训练时动态场景的真实运动毛线照片的最终任务的出色概括性能。

本文研究了黑盒安全测试配置中基于方案的安全测试算法。对于与不同采样分布共享相同州行动集覆盖的算法，通常认为优先考虑探索高风险状态现象会提高采样效率。我们的提案通过引入不可能的定理来对上述直觉提出异议，该定理可证明显示上述差异的所有安全测试算法，同样具有相同的预期采样效率。此外，对于涵盖不同状态活动集的测试算法，采样效率标准不再适用，因为不同的算法不一定会收敛到相同的终止条件。然后，我们提出了基于几乎安全集合概念的测试攻击性定义，以及一种无偏和有效的算法，比较了测试算法之间的侵略性。还提出了来自两足球运动控制器和车辆决策模块的安全测试的经验观察，以支持提出的理论意义和方法。