In this paper, we propose and showcase, for the first time, monocular multi-view layout estimation for warehouse racks and shelves. Unlike typical layout estimation methods, MVRackLay estimates multi-layered layouts, wherein each layer corresponds to the layout of a shelf within a rack. Given a sequence of images of a warehouse scene, a dual-headed Convolutional-LSTM architecture outputs segmented racks, the front and the top view layout of each shelf within a rack. With minimal effort, such an output is transformed into a 3D rendering of all racks, shelves and objects on the shelves, giving an accurate 3D depiction of the entire warehouse scene in terms of racks, shelves and the number of objects on each shelf. MVRackLay generalizes to a diverse set of warehouse scenes with varying number of objects on each shelf, number of shelves and in the presence of other such racks in the background. Further, MVRackLay shows superior performance vis-a-vis its single view counterpart, RackLay, in layout accuracy, quantized in terms of the mean IoU and mAP metrics. We also showcase a multi-view stitching of the 3D layouts resulting in a representation of the warehouse scene with respect to a global reference frame akin to a rendering of the scene from a SLAM pipeline. To the best of our knowledge, this is the first such work to portray a 3D rendering of a warehouse scene in terms of its semantic components - Racks, Shelves and Objects - all from a single monocular camera.
translated by 谷歌翻译
In multi-agent systems with large number of agents, typically the contribution of each agent to the value of other agents is minimal (e.g., aggregation systems such as Uber, Deliveroo). In this paper, we consider such multi-agent systems where each agent is self-interested and takes a sequence of decisions and represent them as a Stochastic Non-atomic Congestion Game (SNCG). We derive key properties for equilibrium solutions in SNCG model with non-atomic and also nearly non-atomic agents. With those key equilibrium properties, we provide a novel Multi-Agent Reinforcement Learning (MARL) mechanism that minimizes variance across values of agents in the same state. To demonstrate the utility of this new mechanism, we provide detailed results on a real-world taxi dataset and also a generic simulator for aggregation systems. We show that our approach reduces the variance in revenues earned by taxi drivers, while still providing higher joint revenues than leading approaches.
translated by 谷歌翻译
在本文中,我们使用称为BSGD(块随机梯度下降)的非常通用的公式研究凸优化。在每次迭代中,有些但没有必要的参数所有组件都会更新。更新的方向可以是两种可能性之一:(i)使用一阶近似计算的噪声浪费的测量,或(ii)使用可能被噪声损坏的函数值计算的近似梯度。该公式包含大多数当前使用的随机梯度方法。我们基于随机近似理论,建立了BSGD收敛到全局最小值的条件。然后,我们通过数值实验来验证预测的收敛性。结果结果表明,当使用近似梯度时,BSGD会收敛,而基于动量的方法可能会差异。但是,不仅是我们的BSGD,还包括标准(全级别)梯度下降,以及各种基于动量的方法,即使有嘈杂的梯度也收敛。
translated by 谷歌翻译
为了分析多维数据的丰富,已经开发了张量的框架。传统上,矩阵奇异值分解(SVD)用于从包含矢量化数据的矩阵中提取最主导的特征。虽然SVD对可以适当表示为矩阵的数据非常有用,但是矢量化步骤导致我们丢失了数据内在的高维关系。为了便于高效的多维特征提取,我们利用了使用基于投影的分类算法,使用T-SVDM,矩阵SVD的张量模拟。我们的作品扩展了T-SVDM框架和分类算法,最初提出了所有数量的尺寸。然后,我们使用Starplus FMRI DataSet将此算法应用于分类任务。我们的数值实验表明,基于张于FMRI分类的卓越方法,而不是基于最佳的等效矩阵的方法。我们的结果说明了我们选择的张量框架的优势,提供了对参数的有益选择的洞察力,并且可以进一步开发用于分类更复杂的成像数据。我们在https://github.com/elizabethnewman/tensor-fmri提供我们的Python实现。
translated by 谷歌翻译
现代软件系统和产品越来越依赖机器学习模型,以基于与用户和系统的交互进行数据驱动的决策,例如计算基础架构。对于更广泛的采用,这种做法必须(i)容纳没有ML背景的软件工程师,并提供(ii)提供优化产品目标的机制。在这项工作中,我们描述了一般原则和特定的端到端毫升平台,为决策和反馈集合提供易于使用的API。循环仪支持从在线数据收集到模拟培训,部署,推理的完整端到端ML生命周期,并扩展支持和调整产品目标的评估和调整。我们概述了平台架构和生产部署的整体影响 - 循环仪当前托管700毫升型号,每秒达到600万决定。我们还描述了学习曲线并总结了平台采用者的经验。
translated by 谷歌翻译
随机近似算法是一种广泛使用的概率方法,用于查找矢量值构造的零,仅当函数的嘈杂测量值可用时。在迄今为止的文献中,可以区分“同步”更新,从而每次更新当前猜测的每个组件,以及'“同步”更新,从而更新一个组件。原则上,也可以在每次瞬间更新一些但不是全部的$ \ theta_t $的组件,这些组件可能被称为“批处理异步随机近似”(BASA)。另外,还可以在使用“本地”时钟与“全局”时钟之间有所区别。在本文中,我们提出了一种统一的配方异步随机近似(BASA)算法,并开发了一种通用方法,以证明这种算法会融合,而与使用是否使用了全球或本地时钟。这些融合证明利用了比现有结果较弱的假设。例如:当使用本地时钟时,现有的收敛证明要求测量噪声是I.I.D序列。在这里,假定测量误差形成了martingale差异序列。同样,迄今为止的所有结果都假设随机步骤大小满足了罗宾斯 - 单月条件的概率类似物。我们通过基础马尔可夫流程的不可约性的纯粹确定性条件代替了这一点。作为加固学习的特定应用,我们介绍了时间差算法$ td(0)$的``批次''版本,以进行价值迭代,以及$ q $ - 学习算法,以查找最佳操作值函数,还允许使用本地时钟而不是全局时钟。在所有情况下,我们在温和的条件下都比现有文献建立了这些算法的融合。
translated by 谷歌翻译
最佳决策要求分类器产生与其经验准确性一致的不确定性估计。然而,深度神经网络通常在他们的预测中受到影响或过度自信。因此,已经开发了方法,以改善培训和后HOC期间的预测性不确定性的校准。在这项工作中,我们提出了可分解的损失,以改善基于频流校准误差估计底层的钻孔操作的软(连续)版本的校准。当纳入训练时,这些软校准损耗在多个数据集中实现最先进的单一模型ECE,精度低于1%的数量。例如,我们观察到ECE的82%(相对于HOC后射出ECE 70%),以换取相对于CIFAR-100上的交叉熵基线的准确性0.7%的相对降低。在培训后结合时,基于软合成的校准误差目标会改善温度缩放,一种流行的重新校准方法。总体而言,跨损失和数据集的实验表明,使用校准敏感程序在数据集移位下产生更好的不确定性估计,而不是使用跨熵损失和后HOC重新校准方法的标准做法。
translated by 谷歌翻译
In the Priority $k$-Center problem, the input consists of a metric space $(X,d)$, an integer $k$, and for each point $v \in X$ a priority radius $r(v)$. The goal is to choose $k$-centers $S \subseteq X$ to minimize $\max_{v \in X} \frac{1}{r(v)} d(v,S)$. If all $r(v)$'s are uniform, one obtains the $k$-Center problem. Plesn\'ik [Plesn\'ik, Disc. Appl. Math. 1987] introduced the Priority $k$-Center problem and gave a $2$-approximation algorithm matching the best possible algorithm for $k$-Center. We show how the problem is related to two different notions of fair clustering [Harris et al., NeurIPS 2018; Jung et al., FORC 2020]. Motivated by these developments we revisit the problem and, in our main technical contribution, develop a framework that yields constant factor approximation algorithms for Priority $k$-Center with outliers. Our framework extends to generalizations of Priority $k$-Center to matroid and knapsack constraints, and as a corollary, also yields algorithms with fairness guarantees in the lottery model of Harris et al [Harris et al, JMLR 2019].
translated by 谷歌翻译