测试时间增强 - 跨测试输入示例的预测的聚合 - 是一种改善图像分类模型性能的既定技术。重要的是，TTA可用于改善事后模型性能，而无需额外的培训。尽管可以将测试时间增强（TTA）应用于任何数据模式，但它在NLP中的采用有限，部分原因是难以识别标签保护转换。在本文中，我们提出的增强政策可以通过语言模型进行大量准确的改进。一个关键发现是，增强政策设计（例如，从单个，非确定性增强产生的样本数量）对TTA的好处有很大的影响。跨二进制分类任务和数据集进行的实验表明，测试时间的增加可以对当前最新方法进行一致的改进。

估计医疗状况的患病率或发生的人口比例是医疗保健和公共卫生中的一个基本问题。准确地估计各组之间的相对患病率（例如，捕获疾病比男性更频繁地影响女性）促进了有效且公平的健康政策，这些政策优先考虑那些受疾病影响不成比例的群体。但是，当医疗状况低估时，很难估计相对患病率。在这项工作中，我们提供了一种基于积极未标记的学习框架的基础，可以准确估计不足以说明的医疗状况的相对患病率。我们表明，在普遍做出的协变量假设下 - 即，以症状为条件的疾病的可能性在整个群体之间保持恒定 - 我们可以恢复相对的患病率，即使没有限制性的假设，通常是在正面的未标记的学习中，即使没有限制性假设无法恢复绝对患病率。我们提供了一系列关于合成和实际健康数据的实验，这些实验证明了我们方法比基线更准确地恢复相对患病率的能力，该方法的鲁棒性具有合理的违反协变量偏移假设的侵犯。

现代机器学习系统越来越多地以广泛的个人数据收集为特征，尽管回报降低并增加了这种做法的社会成本。然而，数据最小化是欧盟一般数据保护法规（'GDPR'）中列出的核心数据保护原则之一，并要求仅处理足够，相关且仅限于必要物品的个人数据。但是，由于缺乏技术解释，该原则的采用有限。在这项工作中，我们以机器学习和法律的文献为基础提出FIDO，这是抑制数据过度收集的框架。 Fido学会了基于与系统性能相关的数据最小化的解释来限制数据收集。具体而言，Fido通过迭代更新性能曲线的估计值或数据集大小和性能之间的关系，从而提供了数据收集，以停止标准。 FIDO通过分段功率定律技术估算性能曲线，该技术在整个数据收集过程中分别对算法性能的不同阶段进行建模。经验实验表明，该框架会产生准确的性能曲线和数据收集，从而在数据集中停止标准并功能采集算法。我们进一步证明，许多其他曲线家庭系统地高估了其他数据的回报。在设计数据最小化框架时，我们的调查结果和分析提供了对相关考虑因素的更深入的见解，包括主动功能获取对单个用户的影响以及用户特定数据最小化的可行性。我们以实施数据最小化的实用建议得出结论。

Quantum state tomography aims to estimate the state of a quantum mechanical system which is described by a trace one, Hermitian positive semidefinite complex matrix, given a set of measurements of the state. Existing works focus on estimating the density matrix that represents the state, using a compressive sensing approach, with only fewer measurements than that required for a tomographically complete set, with the assumption that the true state has a low rank. One very popular method to estimate the state is the use of the Singular Value Thresholding (SVT) algorithm. In this work, we present a machine learning approach to estimate the quantum state of n-qubit systems by unrolling the iterations of SVT which we call Learned Quantum State Tomography (LQST). As merely unrolling SVT may not ensure that the output of the network meets the constraints required for a quantum state, we design and train a custom neural network whose architecture is inspired from the iterations of SVT with additional layers to meet the required constraints. We show that our proposed LQST with very few layers reconstructs the density matrix with much better fidelity than the SVT algorithm which takes many hundreds of iterations to converge. We also demonstrate the reconstruction of the quantum Bell state from an informationally incomplete set of noisy measurements.

Virtual Product placement(VPP) is the advertising technique of digitally placing a branded object into the scene of a movie or TV show. This type of advertising provides the ability for brands to reach consumers without interrupting the viewing experience with a commercial break, as the products are seen in the background or as props. Despite this being a billion-dollar industry, ad rendering technique is currently executed at post production stage, manually either with the help of VFx artists or through semi-automated solutions. In this paper, we demonstrate a fully automated framework to digitally place 2-D ads in linear TV cooking shows captured using single-view camera with small camera movements. Without access to full video or production camera configuration, this framework performs the following tasks (i) identifying empty space for 2-D ad placement (ii) kitchen scene understanding (iii) occlusion handling (iv) ambient lighting and (v) ad tracking.

Modern Deep Learning (DL) models have grown to sizes requiring massive clusters of specialized, high-end nodes to train. Designing such clusters to maximize both performance and utilization to amortize their steep cost is a challenging task requiring careful balance of compute, memory, and network resources. Moreover, a plethora of each model's tuning knobs drastically affect the performance, with optimal values often depending on the underlying cluster's characteristics, which necessitates a complex cluster-workload co-design process. To facilitate the design space exploration of such massive DL training clusters, we introduce COMET a holistic cluster design methodology and workflow to jointly study the impact of parallelization strategies and key cluster resource provisioning on the performance of distributed DL training. We develop a step-by-step process to establish a reusable and flexible methodology, and demonstrate its application with a case study of training a Transformer-1T model on a cluster of variable compute, memory, and network resources. Our case study demonstrates COMET's utility in identifying promising architectural optimization directions and guiding system designers in configuring key model and cluster parameters.

PROteolysis TArgeting Chimeras (PROTACs) are an emerging therapeutic modality for degrading a protein of interest (POI) by marking it for degradation by the proteasome. Recent developments in artificial intelligence (AI) suggest that deep generative models can assist with the de novo design of molecules with desired properties, and their application to PROTAC design remains largely unexplored. We show that a graph-based generative model can be used to propose novel PROTAC-like structures from empty graphs. Our model can be guided towards the generation of large molecules (30--140 heavy atoms) predicted to degrade a POI through policy-gradient reinforcement learning (RL). Rewards during RL are applied using a boosted tree surrogate model that predicts a molecule's degradation potential for each POI. Using this approach, we steer the generative model towards compounds with higher likelihoods of predicted degradation activity. Despite being trained on sparse public data, the generative model proposes molecules with substructures found in known degraders. After fine-tuning, predicted activity against a challenging POI increases from 50% to >80% with near-perfect chemical validity for sampled compounds, suggesting this is a promising approach for the optimization of large, PROTAC-like molecules for targeted protein degradation.

我们为视频中的人类活动识别提供了一种学习算法。我们的方法是为无人机视频而设计的，这些视频主要是从包含人类演员以及背景运动的倾斜放置动态摄像机中获得的。通常，人类参与者占据空间分辨率的十分之一。我们的方法同时利用频域表示的好处，信号处理中的经典分析工具以及数据驱动的神经网络。在对视频中的显着静态和动态像素建模之前，我们构建了一个可区分的静态频率掩码，对于动作识别的基本任务至关重要。在启用神经网络之前，我们可以使用这种可区分的掩码，以通过身份损失函数本质地学习分离的特征表示。我们的公式使网络能够固有地计算其层中的分离显着特征。此外，我们提出了一个封装时间相关性和空间内容的成本功能，以对均匀间隔的视频片段中最重要的框架进行采样。我们在UAV人类数据集和NEC无人机数据集上进行了广泛的实验，并证明比最先进的相对改善为5.72％-13.00％，比相应的基线模型进行了14.28％-38.05％。

我们提出了一种新颖的方法，可以将3D人类动画放入3D场景中，同时保持动画中的任何人类场景相互作用。我们使用计算动画中最重要的网格的概念，以与场景进行交互，我们称之为“键框”。这些关键框架使我们能够更好地优化动画在场景中的位置，从而使动画中的互动（站立，铺设，坐着等）与场景的负担相匹配（例如，站在地板上或躺在床上）。我们将我们称为PAAK的方法与先前的方法进行了比较，包括POSA，Prox地面真理和运动合成方法，并通过感知研究突出了我们方法的好处。人类评估者更喜欢我们的PAAK方法，而不是Prox地面真相数据64.6 \％。此外，在直接比较中，与POSA相比，评估者比竞争方法比包括61.5％的竞争方法更喜欢PAAK。

本文研究了在因果图形模型中设计最佳干预措施序列的问题，以最大程度地减少对事后最佳干预的累积后悔。自然，这是一个因果匪徒问题。重点是线性结构方程模型（SEM）和软干预措施的因果匪徒。假定该图的结构是已知的，并且具有$ n $节点。每个节点都假定使用两种线性机制，一种软干预和一种观察性，产生了$ 2^n $可能的干预措施。现有的因果匪徒算法假设，至少完全指定了奖励节点父母的介入分布。但是，有$ 2^n $这样的分布（一个与每个干预措施相对应），即使在中等尺寸的图中也变得越来越高。本文分配了知道这些分布的假设。提出了两种算法，用于常见者（基于UCB）和贝叶斯（基于汤普森采样）的设置。这些算法的关键思想是避免直接估计$ 2^n $奖励分布，而是估算完全指定SEMS（$ n $线性）的参数，并使用它们来计算奖励。在这两种算法中，在噪声和参数空间的有界假设下，累积遗憾的是$ \ tilde {\ cal o}（（（2d）^l l \ sqrt {t}）$，其中$ d $是图的最高度和$ l $是其最长因果路径的长度。