Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.

联合学习（FL）是以保护隐私方式在异质客户设备上进行机器学习的框架。迄今为止，大多数FL算法都在多个回合中学习一个“全局”服务器模型。在每回合中，相同的服务器模型都向所有参与的客户端广播，在本地更新，然后跨客户端进行汇总。在这项工作中，我们提出了一个更一般的过程，客户“选择”了发送给他们的值的程序。值得注意的是，这使客户可以在较小的数据依赖性切片上操作。为了使这种实用性，我们概述了原始的联合选择，该选择可以在现实的FL系统中进行特定于客户的选择。我们讨论了如何使用联合选择进行模型培训，并表明它可以导致通信和客户记忆使用情况的急剧减少，从而有可能使模型的训练太大而无法适合处个设备。我们还讨论了联邦选择对隐私和信任的含义，这反过来影响了可能的系统约束和设计。最后，我们讨论有关模型体系结构，隐私保护技术和实用FL系统的开放问题。

个性化联合学习认为在异质网络中每个客户独有的学习模型。据称，最终的客户特定模型是为了改善联合网络中的准确性，公平性和鲁棒性等指标。但是，尽管该领域有很多工作，但仍不清楚：（1）哪些个性化技术在各种环境中最有效，以及（2）个性化对现实的联合应用程序的真正重要性。为了更好地回答这些问题，我们提出了Motley，这是个性化联合学习的基准。 Motley由一套来自各种问题域的跨设备和跨核管联合数据集组成，以及彻底的评估指标，以更好地理解个性化的可能影响。我们通过比较许多代表性的个性化联合学习方法来建立基准基准。这些最初的结果突出了现有方法的优势和劣势，并为社区提出了几个开放问题。 Motley旨在提供一种可再现的手段，以推进个性化和异质性的联合学习以及转移学习，元学习和多任务学习的相关领域。

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。

联合学习中的一个重要瓶颈是从客户端设备向中央服务器发送模型更新的网络通信成本。我们提出了一种减少这种成本的方法。我们的方法通过适当的通用代码编码量化更新，考虑到其实证分布。因为量化引入错误，所以通过优化平均总比特率和渐变失真的所需权衡来选择量化水平。我们经验证明，尽管是非i.i.d。联邦学习的性质，速率 - 失真边界是跨数据集，优化器，客户端和训练轮的一致，并且在每个设置中，失真可靠地预测模型性能。这允许在许多用例中近乎最佳的显着简单的压缩方案，并且在堆栈溢出下的TOP-K，DRIVE，3LC和QSGD上优于下一词预测基准。

我们研究迭代矢量字段（与自己组成的矢量字段）是保守的。我们提供了这种自我构成保存保守主义的传染媒介领域的明确示例。值得注意的是，这包括与一些广义线性模型相关联的损耗函数的梯度矢量字段。正如我们所展示的那样，表征满足这种条件的传染媒体字段集导致非琐碎的几何问题。在联合学习的背景下，我们表明，当客户端有损耗函数时，其梯度满足这种情况，联合平均相当于代理损失函数上的梯度下降。我们利用这一点来派生联邦学习的新型融合结果。相比之下，我们证明了当客户损失违反此属性时，联合平均可以产生从集中优化不同的行为。最后，我们讨论了我们对联邦学习的分析框架提升的理论和实践问题。

Federated learning is a distributed machine learning paradigm in which a large number of clients coordinate with a central server to learn a model without sharing their own training data. Standard federated optimization methods such as Federated Averaging (FEDAVG) are often difficult to tune and exhibit unfavorable convergence behavior. In non-federated settings, adaptive optimization methods have had notable success in combating such issues. In this work, we propose federated versions of adaptive optimizers, including ADAGRAD, ADAM, and YOGI, and analyze their convergence in the presence of heterogeneous data for general nonconvex settings. Our results highlight the interplay between client heterogeneity and communication efficiency. We also perform extensive experiments on these methods and show that the use of adaptive optimizers can significantly improve the performance of federated learning.

Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data decentralized. FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches. Motivated by the explosive growth in FL research, this paper discusses recent advances and presents an extensive collection of open problems and challenges.

Coronary Computed Tomography Angiography (CCTA) provides information on the presence, extent, and severity of obstructive coronary artery disease. Large-scale clinical studies analyzing CCTA-derived metrics typically require ground-truth validation in the form of high-fidelity 3D intravascular imaging. However, manual rigid alignment of intravascular images to corresponding CCTA images is both time consuming and user-dependent. Moreover, intravascular modalities suffer from several non-rigid motion-induced distortions arising from distortions in the imaging catheter path. To address these issues, we here present a semi-automatic segmentation-based framework for both rigid and non-rigid matching of intravascular images to CCTA images. We formulate the problem in terms of finding the optimal \emph{virtual catheter path} that samples the CCTA data to recapitulate the coronary artery morphology found in the intravascular image. We validate our co-registration framework on a cohort of $n=40$ patients using bifurcation landmarks as ground truth for longitudinal and rotational registration. Our results indicate that our non-rigid registration significantly outperforms other co-registration approaches for luminal bifurcation alignment in both longitudinal (mean mismatch: 3.3 frames) and rotational directions (mean mismatch: 28.6 degrees). By providing a differentiable framework for automatic multi-modal intravascular data fusion, our developed co-registration modules significantly reduces the manual effort required to conduct large-scale multi-modal clinical studies while also providing a solid foundation for the development of machine learning-based co-registration approaches.

Regularising the parameter matrices of neural networks is ubiquitous in training deep models. Typical regularisation approaches suggest initialising weights using small random values, and to penalise weights to promote sparsity. However, these widely used techniques may be less effective in certain scenarios. Here, we study the Koopman autoencoder model which includes an encoder, a Koopman operator layer, and a decoder. These models have been designed and dedicated to tackle physics-related problems with interpretable dynamics and an ability to incorporate physics-related constraints. However, the majority of existing work employs standard regularisation practices. In our work, we take a step toward augmenting Koopman autoencoders with initialisation and penalty schemes tailored for physics-related settings. Specifically, we propose the "eigeninit" initialisation scheme that samples initial Koopman operators from specific eigenvalue distributions. In addition, we suggest the "eigenloss" penalty scheme that penalises the eigenvalues of the Koopman operator during training. We demonstrate the utility of these schemes on two synthetic data sets: a driven pendulum and flow past a cylinder; and two real-world problems: ocean surface temperatures and cyclone wind fields. We find on these datasets that eigenloss and eigeninit improves the convergence rate by up to a factor of 5, and that they reduce the cumulative long-term prediction error by up to a factor of 3. Such a finding points to the utility of incorporating similar schemes as an inductive bias in other physics-related deep learning approaches.