简单的随机动量方法被广泛用于机器学习优化，但它们的良好实践表现与文献中没有理论保证的理论保证相矛盾。在这项工作中，我们的目标是通过表明随机重球动量来弥合理论和实践之间的差距，该动力可以解释为具有动量的随机kaczmarz算法，保留了二次优化问题（确定性）重球动量的快速线性速率，至少在使用足够大的批次大小的小型匹配时。该分析依赖于仔细分解动量过渡矩阵，并使用新的光谱范围浓度界限来进行独立随机矩阵的产物。我们提供数值实验，以证明我们的边界相当锐利。

语言模型既展示了定量的改进，又展示了新的定性功能，随着规模的增加。尽管它们具有潜在的变革性影响，但这些新能力的特征却很差。为了为未来的研究提供信息，为破坏性的新模型能力做准备，并改善社会有害的效果，至关重要的是，我们必须了解目前和近乎未来的能力和语言模型的局限性。为了应对这一挑战，我们介绍了超越模仿游戏基准（Big Bench）。 Big Bench目前由204个任务组成，由132家机构的442位作者贡献。任务主题是多样的，从语言学，儿童发展，数学，常识性推理，生物学，物理学，社会偏见，软件开发等等。 Big-Bench专注于被认为超出当前语言模型的功能的任务。我们评估了OpenAI的GPT型号，Google内部密集变压器体系结构和大型基础上的开关稀疏变压器的行为，跨越了数百万到数十亿个参数。此外，一个人类专家评估者团队执行了所有任务，以提供强大的基准。研究结果包括：模型性能和校准都随规模改善，但绝对的术语（以及与评估者的性能相比）；在模型类中的性能非常相似，尽管带有稀疏性。逐渐和预测的任务通常涉及大量知识或记忆成分，而在临界规模上表现出“突破性”行为的任务通常涉及多个步骤或组成部分或脆性指标；社交偏见通常会随着含糊不清的环境而随着规模而增加，但这可以通过提示来改善。

强化学习算法的实用性由于相对于问题大小的规模差而受到限制，因为学习$ \ epsilon $ -optimal策略的样本复杂性为$ \ tilde {\ omega} \ left（| s | s || a || a || a || a | h^3 / \ eps^2 \ right）$在MDP的最坏情况下，带有状态空间$ S $，ACTION SPACE $ A $和HORIZON $ H $。我们考虑一类显示出低级结构的MDP，其中潜在特征未知。我们认为，价值迭代和低级别矩阵估计的自然组合导致估计误差在地平线上呈指数增长。然后，我们提供了一种新算法以及统计保证，即有效利用了对生成模型的访问，实现了$ \ tilde {o} \ left的样本复杂度（d^5（d^5（| s |+| a |）\），我们有效利用低级结构。对于等级$ d $设置的Mathrm {Poly}（h）/\ EPS^2 \ right）$，相对于$ | s |，| a | $和$ \ eps $的缩放，这是最小值的最佳。与线性和低级别MDP的文献相反，我们不需要已知的功能映射，我们的算法在计算上很简单，并且我们的结果长期存在。我们的结果提供了有关MDP对过渡内核与最佳动作值函数所需的最小低级结构假设的见解。

图神经网络（GNN）在图形上学习节点表示方面表现出很大的力量。但是，他们可能会从训练数据中继承历史偏见，从而导致预测的歧视性偏见。尽管某些工作已经开发出公平的GNN，但其中大多数直接从非图形域借用了公平代表性学习技术，而没有考虑GNN中特征传播引起的敏感属性泄漏的潜在问题。但是，我们从经验上观察到，特征传播可能会改变以前无害特征与敏感特征的相关性。这可以看作是敏感信息的泄漏，可以进一步加剧预测中的歧视。因此，我们根据特征相关性设计了两个特征掩盖策略，以突出考虑特征传播和相关性变化在减轻歧视中的重要性。通过我们的分析，我们提出了公平视图图神经网络（FAIRVGNN），以通过自动识别和掩盖敏感的相关特征来生成特征的公平视图，以考虑特征传播后的相关变化。鉴于博学的公平视图，我们适应编码器的夹紧权重，以避免使用敏感相关的功能。现实世界数据集的实验表明，Fairvgnn在模型实用程序和公平性之间取得了更好的权衡。我们的代码可在https://github.com/yuwvandy/fairvgnn上公开获取。

Autonomous vehicles are being deployed with a spectrum of capability, extending from driver assistance features for the highway in personal vehicles (SAE Level 2+) to fully autonomous fleet ride sharing services operating in complex city environments (SAE Level 4+). This spectrum of autonomy often operates in different physical environments with different degrees of assumed driver in-the-loop oversight and hence have very different system and subsystem requirements. At the heart of SAE Level 2 to 5 systems is localization and mapping, which ranges from road determination for feature geofencing or high-level routing, through lane determination for advanced driver assistance, to where-in-lane positioning for full vehicle control. We assess localization and mapping requirements for different levels of autonomy and supported features. This work provides a framework for system decomposition, including the level of redundancy needed to achieve the target level of safety. We examine several representative autonomous and assistance features and make recommendations on positioning requirements as well map georeferencing and information integrity.

We present Azimuth, an open-source and easy-to-use tool to perform error analysis for text classification. Compared to other stages of the ML development cycle, such as model training and hyper-parameter tuning, the process and tooling for the error analysis stage are less mature. However, this stage is critical for the development of reliable and trustworthy AI systems. To make error analysis more systematic, we propose an approach comprising dataset analysis and model quality assessment, which Azimuth facilitates. We aim to help AI practitioners discover and address areas where the model does not generalize by leveraging and integrating a range of ML techniques, such as saliency maps, similarity, uncertainty, and behavioral analyses, all in one tool. Our code and documentation are available at github.com/servicenow/azimuth.

Science tests competing theories or models by evaluating the similarity of their predictions against observational experience. Thus, how we measure similarity fundamentally determines what we learn. In machine learning and scientific modeling, similarity metrics are used as objective functions. A classic example being mean squared error, which is the optimal measure of similarity when errors are normally distributed and independent and identically distributed (iid). In many cases, however, the error distribution is neither normal nor iid, so it is left to the scientist to determine an appropriate objective. Here, we review how information theory can guide that selection, then demonstrate the approach with a simple hydrologic model.

As Artificial and Robotic Systems are increasingly deployed and relied upon for real-world applications, it is important that they exhibit the ability to continually learn and adapt in dynamically-changing environments, becoming Lifelong Learning Machines. Continual/lifelong learning (LL) involves minimizing catastrophic forgetting of old tasks while maximizing a model's capability to learn new tasks. This paper addresses the challenging lifelong reinforcement learning (L2RL) setting. Pushing the state-of-the-art forward in L2RL and making L2RL useful for practical applications requires more than developing individual L2RL algorithms; it requires making progress at the systems-level, especially research into the non-trivial problem of how to integrate multiple L2RL algorithms into a common framework. In this paper, we introduce the Lifelong Reinforcement Learning Components Framework (L2RLCF), which standardizes L2RL systems and assimilates different continual learning components (each addressing different aspects of the lifelong learning problem) into a unified system. As an instantiation of L2RLCF, we develop a standard API allowing easy integration of novel lifelong learning components. We describe a case study that demonstrates how multiple independently-developed LL components can be integrated into a single realized system. We also introduce an evaluation environment in order to measure the effect of combining various system components. Our evaluation environment employs different LL scenarios (sequences of tasks) consisting of Starcraft-2 minigames and allows for the fair, comprehensive, and quantitative comparison of different combinations of components within a challenging common evaluation environment.

While machine learning models have achieved unprecedented success in real-world applications, they might make biased/unfair decisions for specific demographic groups and hence result in discriminative outcomes. Although research efforts have been devoted to measuring and mitigating bias, they mainly study bias from the result-oriented perspective while neglecting the bias encoded in the decision-making procedure. This results in their inability to capture procedure-oriented bias, which therefore limits the ability to have a fully debiasing method. Fortunately, with the rapid development of explainable machine learning, explanations for predictions are now available to gain insights into the procedure. In this work, we bridge the gap between fairness and explainability by presenting a novel perspective of procedure-oriented fairness based on explanations. We identify the procedure-based bias by measuring the gap of explanation quality between different groups with Ratio-based and Value-based Explanation Fairness. The new metrics further motivate us to design an optimization objective to mitigate the procedure-based bias where we observe that it will also mitigate bias from the prediction. Based on our designed optimization objective, we propose a Comprehensive Fairness Algorithm (CFA), which simultaneously fulfills multiple objectives - improving traditional fairness, satisfying explanation fairness, and maintaining the utility performance. Extensive experiments on real-world datasets demonstrate the effectiveness of our proposed CFA and highlight the importance of considering fairness from the explainability perspective. Our code is publicly available at https://github.com/YuyingZhao/FairExplanations-CFA .

Recent research in clustering face embeddings has found that unsupervised, shallow, heuristic-based methods -- including $k$-means and hierarchical agglomerative clustering -- underperform supervised, deep, inductive methods. While the reported improvements are indeed impressive, experiments are mostly limited to face datasets, where the clustered embeddings are highly discriminative or well-separated by class (Recall@1 above 90% and often nearing ceiling), and the experimental methodology seemingly favors the deep methods. We conduct a large-scale empirical study of 17 clustering methods across three datasets and obtain several robust findings. Notably, deep methods are surprisingly fragile for embeddings with more uncertainty, where they match or even perform worse than shallow, heuristic-based methods. When embeddings are highly discriminative, deep methods do outperform the baselines, consistent with past results, but the margin between methods is much smaller than previously reported. We believe our benchmarks broaden the scope of supervised clustering methods beyond the face domain and can serve as a foundation on which these methods could be improved. To enable reproducibility, we include all necessary details in the appendices, and plan to release the code.