人工智能(AI)系统越来越多地用于提供建议以促进人类决策。尽管大量工作探讨了如何优化AI系统以产生准确且公平的建议以及如何向人类决策者提供算法建议,但在这项工作中,我们提出了一个不同的基本问题:何时应该提供建议?由于当前不断提供算法建议的局限性的限制,我们提出了以双向方式与人类用户互动的AI系统的设计。我们的AI系统学习使用过去的人类决策为政策提供建议。然后,对于新案例,学识渊博的政策利用人类的意见来确定算法建议将是有用的案例,以及人类最好单独决定的情况。我们通过使用美国刑事司法系统的数据对审前释放决策进行大规模实验来评估我们的方法。在我们的实验中,要求参与者评估被告违反其释放条款的风险,如果释放,并受到不同建议方法的建议。结果表明,与固定的非交互式建议方法相比,我们的交互式辅助方法可以在需要时提供建议,并显着改善人类决策。我们的方法在促进人类学习,保留人类决策者的互补优势以及对建议的更积极反应方面具有额外的优势。
translated by 谷歌翻译
我们考虑了贝叶斯的预测汇总模型,在观察了关于未知二进制事件的私人信号之后,$ n $专家向校长报告了有关事件的后验信念,然后将报告汇总为事件的单个预测。专家的信号和事件的结果遵循校长未知的联合分配,但校长可以访问I.I.D.来自分布的“样本”,每个样本都是专家报告的元组(不是信号)和事件的实现。使用这些样品,主要目的是找到$ \ varepsilon $ - 易于最佳(贝叶斯)聚合器。我们研究此问题的样本复杂性。我们表明,对于任意离散分布,样本的数量必须至少为$ \ tilde \ omega(m^{n-2} / \ varepsilon)$,其中$ m $是每个专家信号空间的大小。该样本复杂性在专家$ n $的数量中成倍增长。但是,如果专家的信号是独立的,以实现事件的实现为条件,那么样本复杂性将大大降低到$ \ tilde o(1 / \ varepsilon^2)$,这不取决于$ n $。
translated by 谷歌翻译
我们提出了一种小说的无参考质量评估度量,图像转移点云质量评估(IT-PCQA),用于3D点云。对于质量评估,深度神经网络(DNN)在无参考度量设计上显示了令人信服的性能。但是,无引用PCQA最具挑战性的问题是我们缺乏大规模的主观数据库来驱动强大的网络。我们的动机是人类视觉系统(HVS)是决策者,无论质量评估的媒体类型如何。利用自然图像的丰富主观评分,我们可以通过DNN探讨人类感知的评估标准,并将预测的能力转移到3D点云。特别是,我们将自然图像视为源域和点云作为目标域,并通过无监督的对抗域适应推断云质量。为了提取有效的潜在特征并最小化域差异,我们提出了分层特征编码器和条件鉴别网络。考虑到最终目的是回归客观评分,我们在条件鉴别网络中引入了一种新的条件跨熵损失,以惩罚阻碍质量回归网络的收敛的负样本。实验结果表明,该方法可以实现比传统的无参考度量更高的性能,甚至与全引用度量的相当结果。该方法还表明,在没有昂贵和繁琐的主观评估的情况下评估特定媒体内容质量的可行性。
translated by 谷歌翻译
在现实世界数据集中,结果标记歧义和主观性是无处不在的。尽管从业者通常以临时方式将所有数据点(实例)的模棱两可的结果标签结合在一起,以提高多级分类的准确性,但缺乏通过任何最佳标准来指导所有数据点标签组合的原则方法。为了解决这个问题,我们提出了信息理论分类准确性(ITCA),该标准可以在预测准确性(预测标签与实际标签一致)和分类分辨率(可预测的标签)(可预测的标签)之间进行平衡,这是平衡的。指导从业者如何结合模棱两可的结果标签。为了找到ITCA指示的最佳标签组合,我们提出了两种搜索策略:贪婪的搜索和广度优先搜索。值得注意的是,ITCA和两种搜索策略适应所有机器学习分类算法。再加上分类算法和搜索策略,ITCA有两个用途:提高预测准确性并识别模棱两可的标签。我们首先通过两种搜索策略来找到合成和真实数据的正确标签组合,首先验证ITCA是否可以实现高精度。然后,我们证明了ITCA在各种应用中的有效性,包括医学预后,癌症存活预测,用户人口统计预测和细胞类型分类。我们还通过研究Oracle和线性判别分析分类算法来提供对ITCA的理论见解。 Python软件包ITCA(可在https://github.com/jsb-ucla/itca上找到)ITCA和搜索策略。
translated by 谷歌翻译
在真实的拍卖中,广泛观察到的现象是胜利者的诅咒 - 获胜者的高价暗示意味着获胜者经常过度估计良好的销售价值,导致突起的负效用。 Eyster和Rabin的Ominominal工作[CommoleTrica'05]介绍了一种旨在解释这一观察到的异常的行为模型。我们举办展示这一偏见“诅咒代理”的代理商。我们采用其模型在相互依存的价值设定中,并旨在设计防止被诅咒的药剂获得负效用的机制。我们设计被诅咒的前后IC的机制,即使他们被诅咒而激励代理人,同时确保结果是单独理性的 - 代理商支付的价格不仅仅是代理商的真实价格价值。由于代理人可能会过度估计良好的价值,因此这种机制可能要求卖方对代理商进行积极转移,以防止代理商过度支付。对于收入最大化,我们提供了最佳的确定性和匿名机制。对于福利最大化,我们需要前后预算平衡(EPBB),因为阳性转移可能导致负收入。我们提出了一种掩蔽操作,采用任何确定性机制,并强加卖方不会使阳性转移,实施EPBB。我们表明,在典型的设置中,EPBB意味着该机制不能制造任何正传输,这意味着应用于全面有效机制上的掩蔽操作会导致社会最佳的EPBB机制。这进一步意味着,如果估值函数是代理信号的最大值,则最佳EPBB机制获得零福利。相比之下,我们表明,对于包括加权估值和L_P-NURMS的总和凹版估值,福利最佳EPBB机制获得最佳福利的一半,因为当代理的数量变大。
translated by 谷歌翻译
众包使预测来自分布式人群的各种预测任务的征集。如何汇总征集的预测,这些预测可能因质量而异,准确的最终预测仍然是一个具有挑战性的问题。研究发现,重量专家预测更多聚集可以提高聚合预测的准确性。但是,这种方法通常需要访问通常不可用的预测员的历史性能数据。在本文中,我们研究了在没有历史性能数据的情况下聚合预测的问题。我们建议使用对等预测方法,是最初旨在在没有地面真理核查的情况下如实地引发私人信息的机制,以评估预报员的专业知识,然后使用此评估来改善预测聚集。我们评估我们的对等预测辅助聚合器的多种14个人预测数据集。与各种现有的聚合器相比,我们的聚合器可以实现通过Brider评分和日志分数测量的聚集精度的显着和一致的改进。我们的结果揭示了识别专家的有效性即使没有历史数据,即使没有历史数据也是即使没有历史数据。
translated by 谷歌翻译
Graph Neural Networks (GNNs) have shown satisfying performance on various graph learning tasks. To achieve better fitting capability, most GNNs are with a large number of parameters, which makes these GNNs computationally expensive. Therefore, it is difficult to deploy them onto edge devices with scarce computational resources, e.g., mobile phones and wearable smart devices. Knowledge Distillation (KD) is a common solution to compress GNNs, where a light-weighted model (i.e., the student model) is encouraged to mimic the behavior of a computationally expensive GNN (i.e., the teacher GNN model). Nevertheless, most existing GNN-based KD methods lack fairness consideration. As a consequence, the student model usually inherits and even exaggerates the bias from the teacher GNN. To handle such a problem, we take initial steps towards fair knowledge distillation for GNNs. Specifically, we first formulate a novel problem of fair knowledge distillation for GNN-based teacher-student frameworks. Then we propose a principled framework named RELIANT to mitigate the bias exhibited by the student model. Notably, the design of RELIANT is decoupled from any specific teacher and student model structures, and thus can be easily adapted to various GNN-based KD frameworks. We perform extensive experiments on multiple real-world datasets, which corroborates that RELIANT achieves less biased GNN knowledge distillation while maintaining high prediction utility.
translated by 谷歌翻译
This paper presents a comprehensive survey of low-light image and video enhancement. We begin with the challenging mixed over-/under-exposed images, which are under-performed by existing methods. To this end, we propose two variants of the SICE dataset named SICE_Grad and SICE_Mix. Next, we introduce Night Wenzhou, a large-scale, high-resolution video dataset, to address the issue of the lack of a low-light video dataset that discount the use of low-light image enhancement (LLIE) to videos. The Night Wenzhou dataset is challenging since it consists of fast-moving aerial scenes and streetscapes with varying illuminations and degradation. We conduct extensive key technique analysis and experimental comparisons for representative LLIE approaches using these newly proposed datasets and the current benchmark datasets. Finally, we address unresolved issues and propose future research topics for the LLIE community.
translated by 谷歌翻译
Online learning naturally arises in many statistical and machine learning problems. The most widely used methods in online learning are stochastic first-order algorithms. Among this family of algorithms, there is a recently developed algorithm, Recursive One-Over-T SGD (ROOT-SGD). ROOT-SGD is advantageous in that it converges at a non-asymptotically fast rate, and its estimator further converges to a normal distribution. However, this normal distribution has unknown asymptotic covariance; thus cannot be directly applied to measure the uncertainty. To fill this gap, we develop two estimators for the asymptotic covariance of ROOT-SGD. Our covariance estimators are useful for statistical inference in ROOT-SGD. Our first estimator adopts the idea of plug-in. For each unknown component in the formula of the asymptotic covariance, we substitute it with its empirical counterpart. The plug-in estimator converges at the rate $\mathcal{O}(1/\sqrt{t})$, where $t$ is the sample size. Despite its quick convergence, the plug-in estimator has the limitation that it relies on the Hessian of the loss function, which might be unavailable in some cases. Our second estimator is a Hessian-free estimator that overcomes the aforementioned limitation. The Hessian-free estimator uses the random-scaling technique, and we show that it is an asymptotically consistent estimator of the true covariance.
translated by 谷歌翻译
In this work we propose a novel token-based training strategy that improves Transformer-Transducer (T-T) based speaker change detection (SCD) performance. The conventional T-T based SCD model loss optimizes all output tokens equally. Due to the sparsity of the speaker changes in the training data, the conventional T-T based SCD model loss leads to sub-optimal detection accuracy. To mitigate this issue, we use a customized edit-distance algorithm to estimate the token-level SCD false accept (FA) and false reject (FR) rates during training and optimize model parameters to minimize a weighted combination of the FA and FR, focusing the model on accurately predicting speaker changes. We also propose a set of evaluation metrics that align better with commercial use cases. Experiments on a group of challenging real-world datasets show that the proposed training method can significantly improve the overall performance of the SCD model with the same number of parameters.
translated by 谷歌翻译