The concept of walkable urban development has gained increased attention due to its public health, economic, and environmental sustainability benefits. Unfortunately, land zoning and historic under-investment have resulted in spatial inequality in walkability and social inequality among residents. We tackle the problem of Walkability Optimization through the lens of combinatorial optimization. The task is to select locations in which additional amenities (e.g., grocery stores, schools, restaurants) can be allocated to improve resident access via walking while taking into account existing amenities and providing multiple options (e.g., for restaurants). To this end, we derive Mixed-Integer Linear Programming (MILP) and Constraint Programming (CP) models. Moreover, we show that the problem's objective function is submodular in special cases, which motivates an efficient greedy heuristic. We conduct a case study on 31 underserved neighborhoods in the City of Toronto, Canada. MILP finds the best solutions in most scenarios but does not scale well with network size. The greedy algorithm scales well and finds near-optimal solutions. Our empirical evaluation shows that neighbourhoods with low walkability have a great potential for transformation into pedestrian-friendly neighbourhoods by strategically placing new amenities. Allocating 3 additional grocery stores, schools, and restaurants can improve the "WalkScore" by more than 50 points (on a scale of 100) for 4 neighbourhoods and reduce the walking distances to amenities for 75% of all residential locations to 10 minutes for all amenity types. Our code and paper appendix are available at https://github.com/khalil-research/walkability.

The Abstraction and Reasoning Corpus (ARC) aims at benchmarking the performance of general artificial intelligence algorithms. The ARC's focus on broad generalization and few-shot learning has made it difficult to solve using pure machine learning. A more promising approach has been to perform program synthesis within an appropriately designed Domain Specific Language (DSL). However, these too have seen limited success. We propose Abstract Reasoning with Graph Abstractions (ARGA), a new object-centric framework that first represents images using graphs and then performs a search for a correct program in a DSL that is based on the abstracted graph space. The complexity of this combinatorial search is tamed through the use of constraint acquisition, state hashing, and Tabu search. An extensive set of experiments demonstrates the promise of ARGA in tackling some of the complicated object-centric tasks of the ARC rather efficiently, producing programs that are correct and easy to understand.

表达性和计算便宜的两分图神经网络（GNN）已被证明是基于深度学习的混合成分线性程序（MILP）求解器的重要组成部分。最近的工作证明了此类GNN在分支结合（B＆B）求解器中取代分支（可变选择）启发式方面的有效性。这些GNN经过训练，离线和集合，以模仿一个非常好但计算昂贵的分支启发式，强大的分支。鉴于B＆B会导致子隔间树，我们问（a）目标启发式启发式在B＆B树的邻近节点之间是否存在很强的依赖性，并且（b）如果是这样，我们是否可以将它们合并到我们的培训程序。具体来说，我们发现，有了强大的分支启发式，孩子节点的最佳选择通常是父母的第二好的选择。我们将其称为“回顾”现象。令人惊讶的是，Gasse等人的典型分支GNN。 （2019年）经常错过这个简单的“答案”。为了通过将回顾现象纳入GNN来更紧密地模仿目标行为，我们提出了两种方法：（a）标准跨凝性损失函数的目标平滑，（b）添加父级（PAT）target（PAT）回顾量学期。最后，我们提出了一个模型选择框架，以结合更难构建的目标，例如在最终模型中解决时间。通过对标准基准实例进行广泛的实验，我们表明我们的提案导致B＆B树大小的22％减少，并且在解决时间的解决方案中提高了15％。

在确定性优化中，通常假定问题的所有参数都是固定和已知的。但是，实际上，某些参数可能是未知的先验参数，但可以从历史数据中估算。典型的预测 - 优化方法将预测和优化分为两个阶段。最近，端到端的预测到优化已成为有吸引力的替代方法。在这项工作中，我们介绍了PYEPO软件包，这是一个基于Pytorch的端到端预测，然后在Python中进行了优化的库。据我们所知，PYEPO（发音为“带有静音” n“”的“菠萝”）是线性和整数编程的第一个通用工具，具有预测的目标函数系数。它提供了两种基本算法：第一种基于Elmachtoub＆Grigas（2021）的开创性工作的凸替代损失函数，第二个基于Vlastelica等人的可区分黑盒求解器方法。 （2019）。 PYEPO提供了一个简单的接口，用于定义新的优化问题，最先进的预测 - 优化训练算法，自定义神经网络体系结构的使用以及端到端方法与端到端方法与与端到端方法的比较两阶段的方法。 PYEPO使我们能够进行一系列全面的实验，以比较沿轴上的多种端到端和两阶段方法，例如预测准确性，决策质量和运行时间，例如最短路径，多个背包和旅行等问题销售人员问题。我们讨论了这些实验中的一些经验见解，这些见解可以指导未来的研究。 PYEPO及其文档可在https://github.com/khalil-research/pyepo上找到。

在混合整数线性编程（MIP）中，A（强）后门是实例的整数变量的“小”子集，具有以下属性：在分支和结合过程中，可以通过仅通过分支来求解该实例到全局最优性。在后门中的变量上。为广泛使用的MIP基准集或特定问题构建预计的后门数据集，家庭可以在MIP的新结构属性上引起新的问题，或者解释为什么在理论上很难在实践中有效解决问题的问题。现有用于查找后门的算法依赖于以各种方式对候选变量子集进行采样，这种方法证明了MIPLIB2003和MIPLIB2010的某些实例的后门存在。但是，由于勘探和剥削之间的不平衡，这些算法在任务中始终取得成功。我们建议BAMCTS，这是一个蒙特卡洛树搜索框架，用于寻找MIPS的后门。广泛的算法工程，与传统MIP概念的杂交以及与CPLEX求解器的密切集成使我们的方法能够超过MIPLIB2017实例的基础线，从而更频繁，更有效地找到后门。

广泛适用的在线匹配问题中的挑战在于在未来输入不确定性时进行不可撤销的作业。大多数理论上的政策本质上都是近视或贪婪。在定期重复匹配过程的实际应用程序中，可以利用基础数据分布来更好地决策。我们提出了一个端到端的强化学习框架，用于根据历史数据的反复试验得出更好的匹配政策。我们设计了一组神经网络体系结构，设计功能表示，并在两个在线匹配问题中对它们进行经验评估：边缘加权的在线双方匹配和在线次级两部分匹配。我们表明，大多数学习方法在四个合成和现实世界数据集上的经典基线算法始终如一地表现更好。平均而言，我们提出的模型在各种合成和现实世界数据集上提高了3-10％的匹配质量。我们的代码可在https://github.com/lyeskhalil/corl上公开获取。

The design of good heuristics or approximation algorithms for NP-hard combinatorial optimization problems often requires significant specialized knowledge and trial-and-error. Can we automate this challenging, tedious process, and learn the algorithms instead? In many real-world applications, it is typically the case that the same optimization problem is solved again and again on a regular basis, maintaining the same problem structure but differing in the data. This provides an opportunity for learning heuristic algorithms that exploit the structure of such recurring problems. In this paper, we propose a unique combination of reinforcement learning and graph embedding to address this challenge. The learned greedy policy behaves like a meta-algorithm that incrementally constructs a solution, and the action is determined by the output of a graph embedding network capturing the current state of the solution. We show that our framework can be applied to a diverse range of optimization problems over graphs, and learns effective algorithms for the Minimum Vertex Cover, Maximum Cut and Traveling Salesman problems.

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

卷积神经网络已在图像分类方面取得了成功的结果，从而实现了超过人类水平的实时结果。但是，纹理图像仍然对这些模型构成一些挑战，例如，在出现这些图像，高层间相似性，没有代表对象的全局观点的几个问题中，培训的数据可用性有限，并且其他。在这种情况下，本文的重点是提高纹理分类中卷积神经网络的准确性。这是通过从验证的神经网络的多个卷积层中提取特征并使用Fisher载体聚集此类特征来完成的。使用较早卷积层的特征的原因是获得了较少域的信息。我们验证方法对基准数据集的纹理分类以及巴西植物物种识别的实际任务的有效性。在这两种情况下，在多层上计算出的Fisher矢量都优于制作方法，证实早期卷积层提供了有关分类纹理图像的重要信息。

本文介绍了适用于各种实用多机器人应用的分布式算法。在这种多机器人应用中，使命的用户定义目标可以作为一般优化问题投射，而无需每个不同机器人的子任务的明确指南。由于环境未知，未知的机器人动态，传感器非线性等，优化成本函数的分析形式不可用。因此，标准梯度 - 下降样算法不适用于这些问题。为了解决这个问题，我们介绍了一种新的算法，仔细设计每个机器人的子变速功能，优化可以实现整个团队目标。在该转换时，我们提出了一种基于基于认知的自适应优化（CAO）算法的分布式方法，其能够近似每个机器人成本函数的演变并充分优化其决策变量（机器人动作）。后者可以通过在线学习来实现影响特派团目标的特定特定特征。总体而言，低复杂性算法可以简单地结合任何类型的操作约束，是容错的，并且可以适当地解决时变的成本函数。这种方法的基石是它与块坐标血管下降算法相同的收敛特征。该算法在多种方案下的三个异构模拟设置中评估，针对通用和特定于问题的算法。源代码可在\ url {https://github.com/athakapo/a-distributed-plug-lobot-applications}中获得。