在过去几年预测和优化的方法(Elmachtoub和Grigas 2021; Wilder,Dilkina和Tambe 2019)受到了不断的关注。这些问题具有预测机器学习(ML)模型的预测的设置,馈送到下游优化问题以进行决策。预测和优化方法建议培训ML模型,通常通过直接优化优化求解器所制作的决策质量。但是,预测和优化方法的一个主要瓶颈正在为每个时代的每个训练实例解决优化问题。为了解决这一挑战,Mulamba等。 (2021)通过缓存可行的解决方案提出噪声对比估计。在这项工作中,我们显示噪声对比估计可以被认为是学习对解决方案缓存进行排名的情况。我们还开发成对和列表排名损失函数,可以以封闭式形式区分,而无需解决优化问题。通过关于这些替代损失职能的培训,我们经验证明我们能够最大限度地减少预测的遗憾。
translated by 谷歌翻译
Developing robots that are capable of many skills and generalization to unseen scenarios requires progress on two fronts: efficient collection of large and diverse datasets, and training of high-capacity policies on the collected data. While large datasets have propelled progress in other fields like computer vision and natural language processing, collecting data of comparable scale is particularly challenging for physical systems like robotics. In this work, we propose a framework to bridge this gap and better scale up robot learning, under the lens of multi-task, multi-scene robot manipulation in kitchen environments. Our framework, named CACTI, has four stages that separately handle data collection, data augmentation, visual representation learning, and imitation policy training. In the CACTI framework, we highlight the benefit of adapting state-of-the-art models for image generation as part of the augmentation stage, and the significant improvement of training efficiency by using pretrained out-of-domain visual representations at the compression stage. Experimentally, we demonstrate that 1) on a real robot setup, CACTI enables efficient training of a single policy capable of 10 manipulation tasks involving kitchen objects, and robust to varying layouts of distractor objects; 2) in a simulated kitchen environment, CACTI trains a single policy on 18 semantic tasks across up to 50 layout variations per task. The simulation task benchmark and augmented datasets in both real and simulated environments will be released to facilitate future research.
translated by 谷歌翻译
Generative Adversarial Networks (GANs) typically suffer from overfitting when limited training data is available. To facilitate GAN training, current methods propose to use data-specific augmentation techniques. Despite the effectiveness, it is difficult for these methods to scale to practical applications. In this work, we present ScoreMix, a novel and scalable data augmentation approach for various image synthesis tasks. We first produce augmented samples using the convex combinations of the real samples. Then, we optimize the augmented samples by minimizing the norms of the data scores, i.e., the gradients of the log-density functions. This procedure enforces the augmented samples close to the data manifold. To estimate the scores, we train a deep estimation network with multi-scale score matching. For different image synthesis tasks, we train the score estimation network using different data. We do not require the tuning of the hyperparameters or modifications to the network architecture. The ScoreMix method effectively increases the diversity of data and reduces the overfitting problem. Moreover, it can be easily incorporated into existing GAN models with minor modifications. Experimental results on numerous tasks demonstrate that GAN models equipped with the ScoreMix method achieve significant improvements.
translated by 谷歌翻译
随着商业光场(LF)摄像机的可用性,LF成像已成为计算摄影中的启动技术。然而,由于空间和角度信息的固有多路复用,在基于商业微杆的LF相机中,空间分辨率受到了显着限制。因此,它成为光场摄像头其他应用的主要瓶颈。本文提出了一个预处理的单图像超级分辨率(SISR)网络中的适应模块,以利用强大的SISR模型,而不是使用高度工程的光场成像域特异性超级分辨率模型。自适应模块由子光圈移位块和融合块组成。它是SISR网络中的一种适应性,可以进一步利用LF图像中的空间和角度信息以提高超级分辨率性能。实验验证表明,所提出的方法的表现优于现有的光场超级分辨率算法。与量表因子2的相同审计的SISR模型相比,所有数据集中的PSNR增益也超过1 dB,而PSNR对于量表因子4的增长率为0.6至1 dB。
translated by 谷歌翻译
异质的面部识别(HFR)旨在匹配不同域(例如,可见到近红外图像)的面孔,该面孔已被广泛应用于身份验证和取证方案。但是,HFR是一个具有挑战性的问题,因为跨域差异很大,异质数据对有限和面部属性变化很大。为了应对这些挑战,我们从异质数据增强的角度提出了一种新的HFR方法,该方法称为面部合成,具有身份 - 属性分解(FSIAD)。首先,身份属性分解(IAD)将图像截取到与身份相关的表示和与身份无关的表示(称为属性)中,然后降低身份和属性之间的相关性。其次,我们设计了一个面部合成模块(FSM),以生成大量具有分离的身份和属性的随机组合的图像,以丰富合成图像的属性多样性。原始图像和合成图像均被用于训练HFR网络,以应对挑战并提高HFR的性能。在五个HFR数据库上进行的广泛实验验证了FSIAD的性能比以前的HFR方法更高。特别是,FSIAD以vr@far = 0.01%在LAMP-HQ上获得了4.8%的改善,这是迄今为止最大的HFR数据库。
translated by 谷歌翻译
智能代理人应该有能力利用先前学习的任务中的知识,以便快速有效地学习新任务。元学习方法已成为实现这一目标的流行解决方案。然而,迄今为止,元强化学习(META-RL)算法仅限于具有狭窄任务分布的简单环境。此外,预处理的范式随后进行了微调以适应新任务,这是一种简单而有效的解决方案,这些解决方案是监督和自我监督的学习。这使质疑元学习方法的好处在加强学习中的好处,这通常是以高复杂性为代价的。因此,我们研究了包括Procgen,rlbench和Atari在内的各种基于视觉的基准测试中的元RL方法,在这些基准测试中,对完全新颖的任务进行了评估。我们的发现表明,当对不同任务(而不是相同任务的不同变化)评估元学习方法时,对新任务进行微调的多任务预处理也相同或更好,或者更好,比用meta进行元数据。测试时间适应。这对于将来的研究令人鼓舞,因为多任务预处理往往比Meta-RL更简单和计算更便宜。从这些发现中,我们主张评估未来的Meta-RL方法在更具挑战性的任务上,并包括以简单但强大的基线进行微调预处理。
translated by 谷歌翻译
Decision forests, including random forests and gradient boosting trees, remain the leading machine learning methods for many real-world data problems, specifically on tabular data. However, current standard implementations only operate in batch mode, and therefore cannot incrementally update when more data arrive. Several previous works developed streaming trees and ensembles to overcome this limitation. Nonetheless, we found that those state-of-the-art algorithms suffer from a number of drawbacks, including poor performance on some problems and high memory usage on others. We therefore developed the simplest possible extension of decision trees we could think of: given new data, simply update existing trees by continuing to grow them, and replace some old trees with new ones to control the total number of trees. On three standard datasets, we illustrate that our approach, Stream Decision Forest (SDF), does not suffer from either of the aforementioned limitations. In a benchmark suite containing 72 classification problems (the OpenML-CC18 data suite), we illustrate that our approach often performs as well, and sometimes better even, than the batch mode decision forest algorithm. Thus, SDFs establish a simple standard for streaming trees and forests that could readily be applied to many real-world problems, including those with distribution drift and continual learning.
translated by 谷歌翻译
什么是学习? 20美元^ {st} Centure的学习理论形式化 - 这是人工智能中沉淀的革命 - 主要是在$ \ mathit {in-diversion} $学习,即在假设训练数据被取样的假设下学习与评估分布相同的分配。这种假设使这些理论不足以表征21美元^ $ {st} MENTURE的现实世界数据问题,其通常是通过与培训数据分布(称为公共学习)不同的评估分布来表征。因此,我们通过放松这种假设来对现有可读性的正式定义进行小小的变化。然后,我们介绍$ \ MATHBF {学习\效率} $(LE)来量化学习者能够利用给定问题的数据的金额,无论它是一个或分发的问题如何。然后,我们定义并证明了可读性的广义概念之间的关系,并展示了该框架是如何足够一般的,以表征传输,多任务,元,持续和终身学习。我们希望本统一有助于弥合现实世界问题的实证实践与理论指导之间的差距。最后,因为生物学学习继续胜过机器学习算法的某些挑战,我们讨论了这一框架VI的局限性 - \'A-is-is-is-is-is-is-is-vis,它的形式化生物学学习能力,旨在为未来研究的多个途径。
translated by 谷歌翻译
深度网络和决策林(如随机森林和渐变升级树)分别是用于结构化和表格数据的主要机器学习方法。许多论文在一个或两个不同的域(例如,在100个不同的表格数据设置上)经验上比较了大量分类器(例如,在100个不同的表格数据设置)上。然而,使用最具当代最佳实践的仔细概念和经验比较这两种策略尚未进行。概念上,我们说明两者都可以盈利地被视为“分区和投票”方案。具体地,他们俩学习的表示空间是将特征空间分区到凸多台的联合中。对于推理,每个都决定从激活节点的投票。该配方允许统一对这些方法之间关系的基本理解。凭经验,我们对数百个表格数据设置以及多个视觉和听觉设置进行比较这两种策略。我们的重点是在大多数10,000个样本的数据集上,它代表了大部分科学和生物医学数据集。一般而言,我们发现森林在表格和结构化数据(视觉和试镜)上以小样本尺寸的表现,而深网络在具有较大样本尺寸的结构化数据上更好地进行。这表明可以通过进一步结合森林和网络的进一步结合来实现两种情况的进一步提升。我们将继续在未来几个月内修改此技术报告,并更新结果。
translated by 谷歌翻译