我们理论上和经验地证明，对抗性鲁棒性可以显着受益于半体验学习。从理论上讲，我们重新审视了Schmidt等人的简单高斯模型。这显示了标准和稳健分类之间的示例复杂性差距。我们证明了未标记的数据桥接这种差距：简单的半体验学习程序（自我训练）使用相同数量的达到高标准精度所需的标签实现高的强大精度。经验上，我们增强了CiFar-10，使用50万微小的图像，使用了8000万微小的图像，并使用强大的自我训练来优于最先进的鲁棒精度（i）$ \ ell_ infty $鲁棒性通过对抗培训和（ii）认证$ \ ell_2 $和$ \ ell_ \ infty $鲁棒性通过随机平滑的几个强大的攻击。在SVHN上，添加DataSet自己的额外训练集，删除的标签提供了4到10个点的增益，在使用额外标签的1点之内。

Traditionally, data analysis and theory have been viewed as separate disciplines, each feeding into fundamentally different types of models. Modern deep learning technology is beginning to unify these two disciplines and will produce a new class of predictively powerful space weather models that combine the physical insights gained by data and theory. We call on NASA to invest in the research and infrastructure necessary for the heliophysics' community to take advantage of these advances.

A long-standing goal of machine-learning-based protein engineering is to accelerate the discovery of novel mutations that improve the function of a known protein. We introduce a sampling framework for evolving proteins in silico that supports mixing and matching a variety of unsupervised models, such as protein language models, and supervised models that predict protein function from sequence. By composing these models, we aim to improve our ability to evaluate unseen mutations and constrain search to regions of sequence space likely to contain functional proteins. Our framework achieves this without any model fine-tuning or re-training by constructing a product of experts distribution directly in discrete protein space. Instead of resorting to brute force search or random sampling, which is typical of classic directed evolution, we introduce a fast MCMC sampler that uses gradients to propose promising mutations. We conduct in silico directed evolution experiments on wide fitness landscapes and across a range of different pre-trained unsupervised models, including a 650M parameter protein language model. Our results demonstrate an ability to efficiently discover variants with high evolutionary likelihood as well as estimated activity multiple mutations away from a wild type protein, suggesting our sampler provides a practical and effective new paradigm for machine-learning-based protein engineering.

Point-of-Care Ultrasound (POCUS) refers to clinician-performed and interpreted ultrasonography at the patient's bedside. Interpreting these images requires a high level of expertise, which may not be available during emergencies. In this paper, we support POCUS by developing classifiers that can aid medical professionals by diagnosing whether or not a patient has pneumothorax. We decomposed the task into multiple steps, using YOLOv4 to extract relevant regions of the video and a 3D sparse coding model to represent video features. Given the difficulty in acquiring positive training videos, we trained a small-data classifier with a maximum of 15 positive and 32 negative examples. To counteract this limitation, we leveraged subject matter expert (SME) knowledge to limit the hypothesis space, thus reducing the cost of data collection. We present results using two lung ultrasound datasets and demonstrate that our model is capable of achieving performance on par with SMEs in pneumothorax identification. We then developed an iOS application that runs our full system in less than 4 seconds on an iPad Pro, and less than 8 seconds on an iPhone 13 Pro, labeling key regions in the lung sonogram to provide interpretable diagnoses.

Likelihood-based deep generative models have recently been shown to exhibit pathological behaviour under the manifold hypothesis as a consequence of using high-dimensional densities to model data with low-dimensional structure. In this paper we propose two methodologies aimed at addressing this problem. Both are based on adding Gaussian noise to the data to remove the dimensionality mismatch during training, and both provide a denoising mechanism whose goal is to sample from the model as though no noise had been added to the data. Our first approach is based on Tweedie's formula, and the second on models which take the variance of added noise as a conditional input. We show that surprisingly, while well motivated, these approaches only sporadically improve performance over not adding noise, and that other methods of addressing the dimensionality mismatch are more empirically adequate.

Fine-grained population maps are needed in several domains, like urban planning, environmental monitoring, public health, and humanitarian operations. Unfortunately, in many countries only aggregate census counts over large spatial units are collected, moreover, these are not always up-to-date. We present POMELO, a deep learning model that employs coarse census counts and open geodata to estimate fine-grained population maps with 100m ground sampling distance. Moreover, the model can also estimate population numbers when no census counts at all are available, by generalizing across countries. In a series of experiments for several countries in sub-Saharan Africa, the maps produced with POMELOare in good agreement with the most detailed available reference counts: disaggregation of coarse census counts reaches R2 values of 85-89%; unconstrained prediction in the absence of any counts reaches 48-69%.

Stock and flow diagrams are already an important tool in epidemiology, but category theory lets us go further and treat these diagrams as mathematical entities in their own right. In this chapter we use communicable disease models created with our software, StockFlow.jl, to explain the benefits of the categorical approach. We first explain the category of stock-flow diagrams, and note the clear separation between the syntax of these diagrams and their semantics, demonstrating three examples of semantics already implemented in the software: ODEs, causal loop diagrams, and system structure diagrams. We then turn to two methods for building large stock-flow diagrams from smaller ones in a modular fashion: composition and stratification. Finally, we introduce the open-source ModelCollab software for diagram-based collaborative modeling. The graphical user interface of this web-based software lets modelers take advantage of the ideas discussed here without any knowledge of their categorical foundations.

上下文多臂强盗（MAB）是推荐系统中重要的顺序决策问题。一系列称为土匪（俱乐部）聚集的作品，利用了对用户的协作效果，并显着提高了建议质量。由于应用程序量表的日益增加和对隐私的关注，因此需求不断增加，以使用户数据分散并将匪徒学习推向本地服务器端。但是，现有的俱乐部算法是在中央服务器上可用的集中设置下设计的。我们专注于研究Bandit（FCLUB）问题的联合在线聚类，该问题旨在最大程度地减少遗憾，同时满足隐私和沟通的考虑。我们为群集检测设计了一种新的基于阶段的方案，并为解决此问题的合作强盗学习提供了一种新型的异步通信协议。为了保护用户的隐私，以前的差异隐私（DP）定义不是很合适，我们提出了一个在用户群集级别上起作用的新DP概念。我们提供了严格的证据，以证明我们的算法同时实现（聚类）DP，sublrinear沟通复杂性和sublrinear遗憾。最后，实验评估表明，与基准算法相比，我们的表现出色。

在本文中，我们研究了组合半伴侣（CMAB），并专注于减少遗憾的批量$ k $的依赖性，其中$ k $是可以拉动或触发的武器总数每个回合。首先，对于用概率触发的臂（CMAB-T）设置CMAB，我们发现了一个新颖的（定向）触发概率和方差调制（TPVM）条件，可以替代各种应用程序的先前使用的平滑度条件，例如级联bandsistits bandits bandits。 ，在线网络探索和在线影响最大化。在这种新条件下，我们提出了一种具有方差感知置信区间的BCUCB-T算法，并进行遗憾分析，将$ O（k）$ actival降低到$ o（\ log k）$或$ o（\ log^2 k） ）$在遗憾中，大大改善了上述申请的后悔界限。其次，为了设置具有独立武器的非触发CMAB，我们提出了一种SESCB算法，该算法利用TPVM条件的非触发版本，并完全消除了对$ k $的依赖，以备受遗憾。作为有价值的副产品，本文使用的遗憾分析可以将几个现有结果提高到$ O（\ log K）$的一倍。最后，实验评估表明，与不同应用中的基准算法相比，我们的表现出色。

人们对连续可穿戴生命体征传感器的兴趣越来越大，用于在家中远程监测患者。这些监视器通常与警报系统耦合，当生命体征测量值落在预定义的正常范围之外时，它会触发。生命体征的趋势（例如心率提高）通常表明健康状况恶化，但很少被纳入警报系统中。在这项工作中，我们提出了一种新型的离群检测算法，以识别这种异常生命体征趋势。我们引入了一种基于距离的措施，以比较生命体征轨迹。对于我们数据集中的每个患者，我们将生命体征时间序列分为180分钟的非重叠时期。然后，我们使用动态时间扭曲距离计算了所有时期对之间的距离。每个时期的特征都以其平均成对距离（平均链路距离）到所有其他时期，其距离为较大的距离。我们将此方法应用于1561多个患者小时的飞行员数据集，这些数据集是从最近在Covid-19收缩后出院的8例患者的1561个患者小时。我们表明，离群值时期与后来入院的患者相对应。我们还描述了一个这样的患者如何从正常异常转变为异常。