Diffusion models, which learn to reverse a signal destruction process to generate new data, typically require the signal at each step to have the same dimension. We argue that, considering the spatial redundancy in image signals, there is no need to maintain a high dimensionality in the evolution process, especially in the early generation phase. To this end, we make a theoretical generalization of the forward diffusion process via signal decomposition. Concretely, we manage to decompose an image into multiple orthogonal components and control the attenuation of each component when perturbing the image. That way, along with the noise strength increasing, we are able to diminish those inconsequential components and thus use a lower-dimensional signal to represent the source, barely losing information. Such a reformulation allows to vary dimensions in both training and inference of diffusion models. Extensive experiments on a range of datasets suggest that our approach substantially reduces the computational cost and achieves on-par or even better synthesis performance compared to baseline methods. We also show that our strategy facilitates high-resolution image synthesis and improves FID of diffusion model trained on FFHQ at $1024\times1024$ resolution from 52.40 to 10.46. Code and models will be made publicly available.
translated by 谷歌翻译
This work is concerned with solving neural network-based feedback controllers efficiently for optimal control problems. We first conduct a comparative study of two mainstream approaches: offline supervised learning and online direct policy optimization. Albeit the training part of the supervised learning approach is relatively easy, the success of the method heavily depends on the optimal control dataset generated by open-loop optimal control solvers. In contrast, direct optimization turns the optimal control problem into an optimization problem directly without any requirement of pre-computing, but the dynamics-related objective can be hard to optimize when the problem is complicated. Our results highlight the priority of offline supervised learning in terms of both optimality and training time. To overcome the main challenges, dataset, and optimization, in the two approaches respectively, we complement them and propose the Pre-train and Fine-tune strategy as a unified training paradigm for optimal feedback control, which further improves the performance and robustness significantly. Our code is available at https://github.com/yzhao98/DeepOptimalControl.
translated by 谷歌翻译
While it has long been empirically observed that adversarial robustness may be at odds with standard accuracy and may have further disparate impacts on different classes, it remains an open question to what extent such observations hold and how the class imbalance plays a role within. In this paper, we attempt to understand this question of accuracy disparity by taking a closer look at linear classifiers under a Gaussian mixture model. We decompose the impact of adversarial robustness into two parts: an inherent effect that will degrade the standard accuracy on all classes, and the other caused by the class imbalance ratio, which will increase the accuracy disparity compared to standard training. Furthermore, we also extend our model to the general family of stable distributions. We demonstrate that while the constraint of adversarial robustness consistently degrades the standard accuracy in the balanced class setting, the class imbalance ratio plays a fundamentally different role in accuracy disparity compared to the Gaussian case, due to the heavy tail of the stable distribution. We additionally perform experiments on both synthetic and real-world datasets. The empirical results not only corroborate our theoretical findings, but also suggest that the implications may extend to nonlinear models over real-world datasets.
translated by 谷歌翻译
Image super-resolution is a common task on mobile and IoT devices, where one often needs to upscale and enhance low-resolution images and video frames. While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints. In this Mobile AI challenge, we address this problem and propose the participants to design an efficient quantized image super-resolution solution that can demonstrate a real-time performance on mobile NPUs. The participants were provided with the DIV2K dataset and trained INT8 models to do a high-quality 3X image upscaling. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated edge NPU capable of accelerating quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 60 FPS rate when reconstructing Full HD resolution images. A detailed description of all models developed in the challenge is provided in this paper.
translated by 谷歌翻译
准确的车辆类型分类在智能运输系统中起重要作用。对于统治者而言,重要的是要了解道路状况,通常为交通灯控制系统的贡献,以相应地响应以减轻交通拥堵。新技术和全面数据源,例如航空照片和遥感数据,提供了更丰富,高维的信息。同样,由于深度神经网络技术的快速发展,基于图像的车辆分类方法可以在处理数据时更好地提取基本的客观特征。最近,已经提出了几种深度学习模型来解决该问题。但是,基于纯卷积的传统方法对全球信息提取有限制,而复杂的环境(例如恶劣的天气)严重限制了识别能力。为了在复杂环境下提高车辆类型的分类能力,本研究提出了一种新型连接的卷积变压器在变压器神经网络(密度TNT)框架中,通过堆叠密集连接的卷积网络(Densenet)和变压器(TNT)(TNT)(TNT)(TNT )层。部署了三个区域的数据和四个不同的天气条件以评估识别能力。实验发现,即使在严重的雾气天气条件下,我们提出的车辆分类模型的识别能力也很少。
translated by 谷歌翻译
在混乱的环境中自动二次运动的敏捷飞行需要受到限制的运动计划和控制,但要受翻译和旋转动力学的影响。传统的基于模型的方法通常需要复杂的设计和重型计算。在本文中,我们开发了一种基于深厚的增强学习方法,该方法解决了通过动态狭窄大门飞行的挑战性任务。我们设计了一个模型预测控制器,其自适应跟踪参考参考由深神经网络(DNN)进行了参数。这些参考文献包括遍历时间和四型SE(3)遍历姿势,这些姿势鼓励机器人从各种初始条件中使用最大的安全边缘飞行大门。为了应对在高度动态环境中的训练困难,我们开发了一个增强的学习框架,以有效地训练DNN,从而很好地介绍了各种环境。此外,我们提出了一种二进制搜索算法,该算法允许在线适应(3)对动态门的引用。最后,通过广泛的高保真模拟,我们表明我们的方法对门的速度不确定性具有鲁棒性,并适应了不同的门轨迹和方向。
translated by 谷歌翻译
作为最成功的AI驱动应用程序之一,推荐系统的目的是通过在我们生活的许多方面提供个性化建议,以有效而有效的方式帮助人们做出适当的决定,尤其是针对各种面向人类的在线服务,例如E-商务平台和社交媒体网站。在过去的几十年中,推荐系统的快速发展通过创造经济价值,节省时间和精力以及促进社会利益,从而使人类受益匪浅。但是,最近的研究发现,数据驱动的推荐系统可能会对用户和社会构成严重威胁,例如传播虚假新闻以操纵社交媒体网站中的公众舆论,扩大不公平为代表性不足的团体或在工作匹配服务中的个人,或从建议结果中推断隐私信息。因此,系统的可信赖性一直吸引着各个方面的关注,以减轻推荐系统引起的负面影响,以增强公众对推荐系统技术的信任。在这项调查中,我们提供了可信赖的推荐系统(TREC)的全面概述,特别关注六个最重要的方面;即安全与鲁棒性,非歧视与公平,解释性,隐私,环境福祉以及问责制和可审计性。对于每个方面,我们总结了最近的相关技术,并讨论了潜在的研究方向,以帮助未来实现值得信赖的推荐系统。
translated by 谷歌翻译
在许多现实世界中的机器学习应用中,亚种群的转移存在着极大地存在,指的是包含相同亚种群组的培训和测试分布,但在亚种群频率中有所不同。重要性重新加权是通过对训练数据集中每个样本施加恒定或自适应抽样权重来处理亚种群转移问题的正常方法。但是,最近的一些研究已经认识到,这些方法中的大多数无法改善性能,而不是经验风险最小化,尤其是当应用于过度参数化的神经网络时。在这项工作中,我们提出了一个简单而实用的框架,称为“不确定性感知混合”(UMIX),以根据样品不确定性重新加权“混合”样品来减轻过度参数化模型中的过度拟合问题。基于训练 - 注射器的不确定性估计为每个样品的拟议UMIX配备,以灵活地表征亚群分布。我们还提供有见地的理论分析,以验证UMIX是否在先前的工作中实现了更好的概括界限。此外,我们在广泛的任务上进行了广泛的经验研究,以验证我们方法的有效性,既有定性和定量。
translated by 谷歌翻译
在多代理系统中,植入是一个非常具有挑战性的问题。传统的羊群方法还需要完全了解环境和控制模型。在本文中,我们建议在羊群任务中进化多代理增强学习(EMARL),这是一种混合算法,将合作和竞争与很少的先验知识相结合。至于合作,我们根据BOIDS模型设计了代理商对羊群任务的奖励。在竞争中,具有高健身的代理商被设计为高级代理商,并且那些健身较低的代理商被设计为初中,让初级代理商随机继承了高级代理人的参数。为了加强竞争,我们还设计了一种进化选择机制,该机制在羊群任务中显示出对信用分配的有效性。一系列具有挑战性和自我对比的基准测试的实验结果表明,EMARL显着超过了完整的竞争或合作方法。
translated by 谷歌翻译
我们介绍了一项对自然语言(NL)推理的人类通知,开放域和逻辑上复杂且多样的数据集,配备了一阶逻辑(fol)注释。对开本由1,435个示例(独特的结论)组成,每个示例与487组前提之一搭配,这些场所作为规则,可用于演绎理由,以理解每个结论的有效性。前提和结论的逻辑正确性是通过其平行注释来确保的,这些注释会自动由我们的FOL推理引擎验证。除了主要的NL推理任务外,对开本中的NL-FOL对自动构成了使用FOL作为逻辑形式的新的NL-FOL翻译数据集。我们对广泛的实验系统地评估了对中型语言模型(BERT,ROBERTA)进行微调的FOL推理能力,并且在大型语言模型(GPT-NEOX,OPT,OPT,GPT-3,Codex)上促成了很少的射击。对于NL-FOL翻译,我们尝试使用GPT-3和Codex。我们的结果表明,公开可用的最强大的大语言模型之一(LLM),GPT-3 Davinci,仅比随机结果略好,而在一部分集的一部分中,该模型尤其不好,并且在预测该模型方面尤其不好。纠正虚假和未知结论的真实价值。我们的数据集和代码可在https://github.com/yale-lily/folio上找到。
translated by 谷歌翻译