准确的交通预测对于智能运输系统至关重要。尽管许多深度学习模型已经达到了最新的1小时交通预测，但长期交通预测跨越多小时仍然是一个重大挑战。此外，大多数现有的深度学习流量预测模型都是黑匣子，提出了与解释性和解释性有关的其他挑战。我们开发了图形金字塔自动构造（X-GPA），这是一种基于注意力的空间 - 速率图神经网络，使用了新型金字塔自相关注意机制。它可以从图表上的长时间序列中学习，并提高长期流量预测准确性。与几种最先进的方法相比，我们的模型可以实现高达35％的长期流量预测准确性。 X-GPA模型的基于注意力的分数提供了基于交通动态的空间和时间解释，这些解释会改变正常与高峰时段的流量以及工作日与周末流量的变化。

贝叶斯优化（BO）是一种用于计算昂贵的黑盒优化的方法，例如模拟器校准和深度学习方法的超参数优化。在BO中，采用动态更新的计算廉价替代模型来学习黑框函数的投入输出关系。该替代模型用于探索和利用输入空间的有前途的区域。多点BO方法采用单个经理/多个工人策略，以在较短的时间内实现高质量的解决方案。但是，多点生成方案中的计算开销是设计BO方法的主要瓶颈，可以扩展到数千名工人。我们提出了一种异步分配的BO（ADBO）方法，其中每个工人都会运行搜索，并异步地传达所有其他没有经理的工人的黑框评估的输入输出值。我们将方法扩展到4,096名工人，并证明了解决方案质量和更快的收敛质量。我们证明了我们从Exascale计算项目烛台基准调整神经网络超参数的方法的有效性。

在许多计算科学和工程应用中，与给定输入相对应的感兴趣系统的输出可以在不同的忠诚度中以不同的成本进行查询。通常，低保真数据便宜且丰富，而高保真数据却昂贵且稀缺。在这项工作中，我们研究了具有不同水平的保真度以针对给定的控制任务的多个环境中的强化学习（RL）问题。我们专注于通过多量数据数据提高RL代理的性能。具体而言，提出了利用低度和高保真回报之间的互相关的多重估计器，以减少状态行动值函数估计的差异。所提出的估计量基于控制变体的方法，用于设计一种多因素蒙特卡洛RL（MFMCRL）算法，该算法可改善高保真环境中代理的学习。理论上，通过使用概率范围来分析差异对政策评估和政策改进的影响。我们的理论分析和数值实验表明，对于高保真数据样本的有限预算，我们提出的MFMCRL代理与仅使用高保真环境数据来学习最佳策略的标准RL代理相比，具有出色的性能。

使用来自环路检测器传感器的数据，用于高速公路中交通事故的近实时检测对避免主要交通拥堵至关重要。虽然最近的监督机器学习方法通​​过利用人类标记的入射数据提供事件检测的解决方案，但误报率通常太高而无法在实践中使用。具体而言，事故的人类标签的不一致显着影响了监督学习模型的表现。为此，我们专注于一种以数据为中心的方法来提高准确性，降低高速公路上交通事故检测的误报率。我们开发了一个弱监管学习工作流程，为没有地面真理标签的入射数据生成高质量的训练标签，我们在监督学习设置中使用这些生成的标签进行最终检测。这种方法包括三个阶段。首先，我们介绍一个数据预处理和策策流水线，用于处理流量传感器数据，通过利用标签函数来生成高质量的培训数据，这可以是域知识相关或简单的启发式规则。其次，我们使用三个监督学习模型 - 随机森林，k最近邻居和支持向量机集合和长短期内存分类器来评估由弱监管生成的培训数据。结果表明，在使用受弱监管生成的培训数据后，所有模型的准确性都会显着提高。第三，我们开发了一种在线实时事件检测方法，在检测事件时利用模型集合和不确定性量化。总体而言，我们表明，我们提出的弱监管学习工作流程实现了高事件检测率（0.90）和低误报率（0.08）。

我们考虑非线性优化问题，涉及神经网络代表代理模型。我们首先展示了如何直接将神经网络评估嵌入优化模型中，突出难以防止收敛的方法，然后表征这些模型的平稳性。然后，我们在具有Relu激活的前馈神经网络的特定情况下存在两种替代配方，其具有recu激活：作为混合整数优化问题，作为具有互补限制的数学程序。对于后一种制剂，我们证明了在该问题的点处的有同性，对应于嵌入式制剂的实质性。这些配方中的每一个都可以用最先进的优化方法来解决，并且我们展示了如何为这些方法获得良好的初始可行解决方案。我们将三种实际应用的配方进行比较，在燃烧发动机的设计和控制中产生的三种实际应用，在对分类器网络的对抗攻击中产生的产生，以及在油井网中的最佳流动确定。

深度神经网络是各种任务的强大预测因子。但是，它们不会直接捕捉不确定性。使用神经网络集合来量化不确定性与基于贝叶斯神经网络的方法具有竞争力，同时受益于更好的计算可扩展性。然而，神经网络的构建集合是一个具有挑战性的任务，因为除了为整个集合的每个成员选择正确的神经结构或超参数之外，还有增加训练每个模型的成本。我们提出了一种自动化方法，用于生成深神经网络的集合。我们的方法利用联合神经结构和封锁统计数据搜索来生成合奏。我们使用总方差定律来分解深度集成的预测方差，进入炼层（数据）和认知（模型）的不确定性。我们展示了AutodeUQ优于概率的概率BackProjagation，Monte Carlo辍学，深组合，无分配的集合以及多元回归基准的超集合方法。

Dense prediction tasks such as segmentation and detection of pathological entities hold crucial clinical value in the digital pathology workflow. However, obtaining dense annotations on large cohorts is usually tedious and expensive. Contrastive learning (CL) is thus often employed to leverage large volumes of unlabeled data to pre-train the backbone network. To boost CL for dense prediction, some studies have proposed variations of dense matching objectives in pre-training. However, our analysis shows that employing existing dense matching strategies on histopathology images enforces invariance among incorrect pairs of dense features and, thus, is imprecise. To address this, we propose a precise location-based matching mechanism that utilizes the overlapping information between geometric transformations to precisely match regions in two augmentations. Extensive experiments on two pretraining datasets (TCGA-BRCA, NCT-CRC-HE) and three downstream datasets (GlaS, CRAG, BCSS) highlight the superiority of our method in semantic and instance segmentation tasks. Our method outperforms previous dense matching methods by up to 7.2 % in average precision for detection and 5.6 % in average precision for instance segmentation tasks. Additionally, by using our matching mechanism in the three popular contrastive learning frameworks, MoCo-v2, VICRegL and ConCL, the average precision in detection is improved by 0.7 % to 5.2 % and the average precision in segmentation is improved by 0.7 % to 4.0 %, demonstrating its generalizability.

Information overloading requires the need for summarizers to extract salient information from the text. Currently, there is an overload of dialogue data due to the rise of virtual communication platforms. The rise of Covid-19 has led people to rely on online communication platforms like Zoom, Slack, Microsoft Teams, Discord, etc. to conduct their company meetings. Instead of going through the entire meeting transcripts, people can use meeting summarizers to select useful data. Nevertheless, there is a lack of comprehensive surveys in the field of meeting summarizers. In this survey, we aim to cover recent meeting summarization techniques. Our survey offers a general overview of text summarization along with datasets and evaluation metrics for meeting summarization. We also provide the performance of each summarizer on a leaderboard. We conclude our survey with different challenges in this domain and potential research opportunities for future researchers.

It is known that neural networks have the problem of being over-confident when directly using the output label distribution to generate uncertainty measures. Existing methods mainly resolve this issue by retraining the entire model to impose the uncertainty quantification capability so that the learned model can achieve desired performance in accuracy and uncertainty prediction simultaneously. However, training the model from scratch is computationally expensive and may not be feasible in many situations. In this work, we consider a more practical post-hoc uncertainty learning setting, where a well-trained base model is given, and we focus on the uncertainty quantification task at the second stage of training. We propose a novel Bayesian meta-model to augment pre-trained models with better uncertainty quantification abilities, which is effective and computationally efficient. Our proposed method requires no additional training data and is flexible enough to quantify different uncertainties and easily adapt to different application settings, including out-of-domain data detection, misclassification detection, and trustworthy transfer learning. We demonstrate our proposed meta-model approach's flexibility and superior empirical performance on these applications over multiple representative image classification benchmarks.

In consequential decision-making applications, mitigating unwanted biases in machine learning models that yield systematic disadvantage to members of groups delineated by sensitive attributes such as race and gender is one key intervention to strive for equity. Focusing on demographic parity and equality of opportunity, in this paper we propose an algorithm that improves the fairness of a pre-trained classifier by simply dropping carefully selected training data points. We select instances based on their influence on the fairness metric of interest, computed using an infinitesimal jackknife-based approach. The dropping of training points is done in principle, but in practice does not require the model to be refit. Crucially, we find that such an intervention does not substantially reduce the predictive performance of the model but drastically improves the fairness metric. Through careful experiments, we evaluate the effectiveness of the proposed approach on diverse tasks and find that it consistently improves upon existing alternatives.