从最小值和实例依赖性视图中,已经对乐观算法进行了广泛的研究,以在情节表格MDP中进行遗憾的最小化。但是,对于PAC RL问题,目标是确定具有很高可能性的近乎最佳策略,对它们的实例依赖性样本复杂性知之甚少。 Wagenmaker等人的负面结果。 (2021)表明,乐观的抽样规则不能用于达到(仍然难以捉摸的)最佳实例依赖性样本复杂性。在正面,我们为PAC RL的乐观算法提供了第一个依赖于实例依赖性的结合,BPI-UCRL仅可用的最小值保证(Kaufmann等,2021)。尽管我们的界限具有一些最小的访问概率,但与先前工作中出现的价值差距相比,它的次要差距的精致概念。此外,在具有确定性过渡的MDP中,我们表明BPI-UCRL实际上是近乎最佳的。从技术方面来说,由于独立兴趣的新“目标技巧”,我们的分析非常简单。我们用新颖的硬度结果补充了这些发现,解释了为什么与Minimax政权不同,为什么PAC RL的实例依赖性复杂性与遗憾最小化的复杂性不易与遗憾最小化相关。
translated by 谷歌翻译
出现了前两种算法,作为汤普森采样对多臂匪徒模型中最佳手臂识别的适应(Russo,2016),用于武器的参数家族。他们通过在两个候选臂,一个领导者和一个挑战者中随机化来选择下一个要采样的臂。尽管具有良好的经验表现,但仅当手臂是具有已知差异的高斯时,才能获得固定信心最佳手臂识别的理论保证。在本文中,我们提供了对两种方法的一般分析,该方法确定了领导者,挑战者和武器(可能是非参数)分布的理想特性。结果,我们获得了理论上支持的前两种算法,用于具有有限分布的最佳臂识别。我们的证明方法特别证明了用于选择从汤普森采样继承的领导者的采样步骤可以用其他选择代替,例如选择经验最佳的臂。
translated by 谷歌翻译
在大约正确的(PAC)强化学习(RL)中,需要代理来识别具有$ 1- \ delta $的$ \ epsilon $最佳政策。尽管此问题存在最小值最佳算法,但其实例依赖性复杂性在情节马尔可夫决策过程(MDPS)中仍然难以捉摸。在本文中,我们提出了具有有限状态和动作空间的确定性情节MDP中PAC RL样品复杂性的第一个(几乎)匹配的上限和下限。特别是,我们的界限为国家行动对的新概念构成了我们称为确定性返回差距的新概念。尽管我们的依赖实例的下限是作为线性程序编写的,但我们的算法非常简单,并且在学习过程中不需要解决这样的优化问题。他们的设计和分析采用了新颖的想法,包括图理论概念,例如最小流量和最大削减,我们认为这为这个问题提供了新的启示。
translated by 谷歌翻译
本文提出了新的偏差不等式,其在多武装强盗模型中的自适应采样下均匀地均匀。使用给定的一维指数家庭中的kullback-leibler发散来测量偏差,并且可以一次考虑几个臂。它们是通过基于分层的每个臂鞅构造而构建的,并通过将那些鞅乘以来获得。我们的偏差不平等允许我们根据广义概率比来分析一大类连续识别问题的概要概率比,并且为臂的装置的某些功能构造紧密的置信区间。
translated by 谷歌翻译
Topological data analysis (TDA) is a branch of computational mathematics, bridging algebraic topology and data science, that provides compact, noise-robust representations of complex structures. Deep neural networks (DNNs) learn millions of parameters associated with a series of transformations defined by the model architecture, resulting in high-dimensional, difficult-to-interpret internal representations of input data. As DNNs become more ubiquitous across multiple sectors of our society, there is increasing recognition that mathematical methods are needed to aid analysts, researchers, and practitioners in understanding and interpreting how these models' internal representations relate to the final classification. In this paper, we apply cutting edge techniques from TDA with the goal of gaining insight into the interpretability of convolutional neural networks used for image classification. We use two common TDA approaches to explore several methods for modeling hidden-layer activations as high-dimensional point clouds, and provide experimental evidence that these point clouds capture valuable structural information about the model's process. First, we demonstrate that a distance metric based on persistent homology can be used to quantify meaningful differences between layers, and we discuss these distances in the broader context of existing representational similarity metrics for neural network interpretability. Second, we show that a mapper graph can provide semantic insight into how these models organize hierarchical class knowledge at each layer. These observations demonstrate that TDA is a useful tool to help deep learning practitioners unlock the hidden structures of their models.
translated by 谷歌翻译
For conceptual design, engineers rely on conventional iterative (often manual) techniques. Emerging parametric models facilitate design space exploration based on quantifiable performance metrics, yet remain time-consuming and computationally expensive. Pure optimisation methods, however, ignore qualitative aspects (e.g. aesthetics or construction methods). This paper provides a performance-driven design exploration framework to augment the human designer through a Conditional Variational Autoencoder (CVAE), which serves as forward performance predictor for given design features as well as an inverse design feature predictor conditioned on a set of performance requests. The CVAE is trained on 18'000 synthetically generated instances of a pedestrian bridge in Switzerland. Sensitivity analysis is employed for explainability and informing designers about (i) relations of the model between features and/or performances and (ii) structural improvements under user-defined objectives. A case study proved our framework's potential to serve as a future co-pilot for conceptual design studies of pedestrian bridges and beyond.
translated by 谷歌翻译
Recently, learning-based controllers have been shown to push mobile robotic systems to their limits and provide the robustness needed for many real-world applications. However, only classical optimization-based control frameworks offer the inherent flexibility to be dynamically adjusted during execution by, for example, setting target speeds or actuator limits. We present a framework to overcome this shortcoming of neural controllers by conditioning them on an auxiliary input. This advance is enabled by including a feature-wise linear modulation layer (FiLM). We use model-free reinforcement-learning to train quadrotor control policies for the task of navigating through a sequence of waypoints in minimum time. By conditioning the policy on the maximum available thrust or the viewing direction relative to the next waypoint, a user can regulate the aggressiveness of the quadrotor's flight during deployment. We demonstrate in simulation and in real-world experiments that a single control policy can achieve close to time-optimal flight performance across the entire performance envelope of the robot, reaching up to 60 km/h and 4.5g in acceleration. The ability to guide a learned controller during task execution has implications beyond agile quadrotor flight, as conditioning the control policy on human intent helps safely bringing learning based systems out of the well-defined laboratory environment into the wild.
translated by 谷歌翻译
本文解决了利益区域(ROI)计算机断层扫描(CT)的图像重建问题。尽管基于模型的迭代方法可用于此问题,但由于乏味的参数化和缓慢的收敛性,它们的实用性通常受到限制。另外,当保留的先验不完全适合溶液空间时,可以获得不足的溶液。深度学习方法提供了一种快速的替代方法,从大型数据集中利用信息,因此可以达到高重建质量。但是,这些方法通常依赖于不考虑成像系统物理学的黑匣子,而且它们缺乏可解释性通常会感到沮丧。在两种方法的十字路口,最近都提出了展开的深度学习技术。它们将模型的物理和迭代优化算法纳入神经网络设计中,从而在各种应用中均具有出色的性能。本文介绍了一种新颖的,展开的深度学习方法,称为U-RDBFB,为ROI CT重建而设计为有限的数据。由于强大的非凸数据保真功能与稀疏性诱导正则化功能相结合,因此有效地处理了很少的截断数据。然后,嵌入在迭代重新加权方案中的块双重前向(DBFB)算法的迭代将在神经网络体系结构上展开,从而以监督的方式学习各种参数。我们的实验显示了对各种最新方法的改进,包括基于模型的迭代方案,深度学习体系结构和深度展开的方法。
translated by 谷歌翻译
重建 /特征提取的联合问题是图像处理中的一项具有挑战性的任务。它包括以联合方式执行图像的恢复及其特征的提取。在这项工作中,我们首先提出了一个新颖的非平滑和非凸变性表述。为此,我们介绍了一种通用的高斯先验,其参数(包括其指数)是空间变化的。其次,我们设计了一种基于近端的交替优化算法,该算法有效利用了所提出的非convex目标函数的结构。我们还分析了该算法的收敛性。如在关节分割/脱张任务进行的数值实验中所示,该方法提供了高质量的结果。
translated by 谷歌翻译
计算流体动力学(CFD)可用于模拟血管血流动力学并分析潜在的治疗方案。 CFD已显示对改善患者预后有益。但是,尚未实现CFD的实施CFD。 CFD的障碍包括高计算资源,设计模拟设置所需的专业经验以及较长的处理时间。这项研究的目的是探索使用机器学习(ML)以自动和快速回归模型复制常规主动脉CFD。用于训练/测试的数据该模型由在合成生成的3D主动脉形状上执行的3,000个CFD模拟组成。这些受试者是由基于实际患者特异性主动脉(n = 67)的统计形状模型(SSM)生成的。对200个测试形状进行的推理导致压力和速度的平均误差分别为6.01%+/- 3.12 SD和3.99%+/- 0.93 SD。我们的基于ML的模型在〜0.075秒内执行CFD(比求解器快4,000倍)。这项研究表明,可以使用ML以更快的速度,自动过程和高精度来复制常规血管CFD的结果。
translated by 谷歌翻译