将离散域上的功能集成到神经网络中是开发其推理离散对象的能力的关键。但是，离散域是（1）自然不适合基于梯度的优化，并且（2）与依赖于高维矢量空间中表示形式的深度学习体系结构不相容。在这项工作中，我们解决了设置功能的两个困难，这些功能捕获了许多重要的离散问题。首先，我们开发了将设置功能扩展到低维连续域的框架，在该域中，许多扩展是自然定义的。我们的框架包含许多众所周知的扩展，作为特殊情况。其次，为避免不良的低维神经网络瓶颈，我们将低维扩展转换为高维空间中的表示形式，从半际计划进行组合优化的成功中获得了灵感。从经验上讲，我们观察到扩展对无监督的神经组合优化的好处，特别是具有高维其表示。

大型语言模型已被证明可以使用少量学习来实现各种自然语言任务的出色表现，这大大减少了将模型调整到特定应用程序所需的特定任务培训示例的数量。为了进一步了解量表对少量学习的影响，我们培训了一个5400亿个参数，密集激活的变压器语言模型，我们称之为“途径”语言模型棕榈。我们使用Pathways在6144 TPU V4芯片上训练了Palm，这是一种新的ML系统，可在多个TPU POD上进行高效的训练。我们通过在数百种语言理解和产生基准的基准方面实现最先进的学习结果来证明扩展的持续好处。在这些任务中，Palm 540B实现了突破性的表现，在一系列多步推理任务上表现出色，超过了最新的最新表现，并且在最近发布的Big Benchmark上表现优于平均人类表现。大量的大型基础任务显示出与模型量表的不连续改进，这意味着当我们扩展到最大模型时，性能急剧增加。 Palm在多语言任务和源代码生成方面也具有很强的功能，我们在各种基准测试中证明了这一点。我们还提供了有关偏见和毒性的全面分析，并研究了训练数据记忆的程度，相对于模型量表。最后，我们讨论与大语言模型有关的道德考虑，并讨论潜在的缓解策略。

通过对比学习学到的表示的概括依赖于提取数据的特征。然而，我们观察到，对比损失并不总是充分引导提取的特征，可以通过无意中抑制重要预测特征来对下游任务对下游任务的性能产生负面影响的行为。我们发现特征提取受到所谓的实例歧视任务的难度的影响（即，鉴别不同分数的相似点的任务）。虽然更难以改善一些特征的表示，但改进是以抑制先前良好的特征的成本。作为响应，我们提出了隐含的特征修改（IFM），一种改变正和阴性样本的方法，以便引导对比模型来捕获更广泛的预测特征。凭经验，我们观察到IFM减少了特征抑制，结果提高了视觉和医学成像任务的性能。代码可在：\ url {https://github.com/joshr17/ifm}可用。

A prominent technique for self-supervised representation learning has been to contrast semantically similar and dissimilar pairs of samples. Without access to labels, dissimilar (negative) points are typically taken to be randomly sampled datapoints, implicitly accepting that these points may, in reality, actually have the same label. Perhaps unsurprisingly, we observe that sampling negative examples from truly different labels improves performance, in a synthetic setting where labels are available. Motivated by this observation, we develop a debiased contrastive objective that corrects for the sampling of same-label datapoints, even without knowledge of the true labels. Empirically, the proposed objective consistently outperforms the state-of-the-art for representation learning in vision, language, and reinforcement learning benchmarks. Theoretically, we establish generalization bounds for the downstream classification task.

Understanding the relationship between structure and sentiment is essential in highlighting future operations with online social networks. More specifically, within popular conversation on Twitter. This paper provides a development on the relationship between the two variables: structure, defined as the composition of a directed network, and sentiment, a quantified value of the positive/negative connotations of a conversation. We highlight thread sentiment to be inversely proportional to the strength and connectivity of a network. The second portion of this paper highlights differences in query types, specifically how the aforementioned behavior differs within four key query types. This paper focuses on topical, event-based, geographic, and individual queries as orientations which have differing behavior. Using cross-query analysis, we see that the relationship between structure and sentiment, though still inversely proportional, differs greatly across query types. We find this relationship to be the most clear within the individual queries and the least prevalent within the event-based queries. This paper provides a sociological progression in our understanding of opinion and networks, while providing a methodological advancement for future studies on similar subjects.

We present temporally layered architecture (TLA), a biologically inspired system for temporally adaptive distributed control. TLA layers a fast and a slow controller together to achieve temporal abstraction that allows each layer to focus on a different time-scale. Our design is biologically inspired and draws on the architecture of the human brain which executes actions at different timescales depending on the environment's demands. Such distributed control design is widespread across biological systems because it increases survivability and accuracy in certain and uncertain environments. We demonstrate that TLA can provide many advantages over existing approaches, including persistent exploration, adaptive control, explainable temporal behavior, compute efficiency and distributed control. We present two different algorithms for training TLA: (a) Closed-loop control, where the fast controller is trained over a pre-trained slow controller, allowing better exploration for the fast controller and closed-loop control where the fast controller decides whether to "act-or-not" at each timestep; and (b) Partially open loop control, where the slow controller is trained over a pre-trained fast controller, allowing for open loop-control where the slow controller picks a temporally extended action or defers the next n-actions to the fast controller. We evaluated our method on a suite of continuous control tasks and demonstrate the advantages of TLA over several strong baselines.

Data deprivation, or the lack of easily available and actionable information on the well-being of individuals, is a significant challenge for the developing world and an impediment to the design and operationalization of policies intended to alleviate poverty. In this paper we explore the suitability of data derived from OpenStreetMap to proxy for the location of two crucial public services: schools and health clinics. Thanks to the efforts of thousands of digital humanitarians, online mapping repositories such as OpenStreetMap contain millions of records on buildings and other structures, delineating both their location and often their use. Unfortunately much of this data is locked in complex, unstructured text rendering it seemingly unsuitable for classifying schools or clinics. We apply a scalable, unsupervised learning method to unlabeled OpenStreetMap building data to extract the location of schools and health clinics in ten countries in Africa. We find the topic modeling approach greatly improves performance versus reliance on structured keys alone. We validate our results by comparing schools and clinics identified by our OSM method versus those identified by the WHO, and describe OSM coverage gaps more broadly.

We present a new algorithm for automatically bounding the Taylor remainder series. In the special case of a scalar function $f: \mathbb{R} \mapsto \mathbb{R}$, our algorithm takes as input a reference point $x_0$, trust region $[a, b]$, and integer $k \ge 0$, and returns an interval $I$ such that $f(x) - \sum_{i=0}^k \frac {f^{(i)}(x_0)} {i!} (x - x_0)^i \in I (x - x_0)^{k+1}$ for all $x \in [a, b]$. As in automatic differentiation, the function $f$ is provided to the algorithm in symbolic form, and must be composed of known elementary functions. At a high level, our algorithm has two steps. First, for a variety of commonly-used elementary functions (e.g., $\exp$, $\log$), we derive sharp polynomial upper and lower bounds on the Taylor remainder series. We then recursively combine the bounds for the elementary functions using an interval arithmetic variant of Taylor-mode automatic differentiation. Our algorithm can make efficient use of machine learning hardware accelerators, and we provide an open source implementation in JAX. We then turn our attention to applications. Most notably, we use our new machinery to create the first universal majorization-minimization optimization algorithms: algorithms that iteratively minimize an arbitrary loss using a majorizer that is derived automatically, rather than by hand. Applied to machine learning, this leads to architecture-specific optimizers for training deep networks that converge from any starting point, without hyperparameter tuning. Our experiments show that for some optimization problems, these hyperparameter-free optimizers outperform tuned versions of gradient descent, Adam, and AdaGrad. We also show that our automatically-derived bounds can be used for verified global optimization and numerical integration, and to prove sharper versions of Jensen's inequality.

A typical product or place often has hundreds of reviews, and summarization of these texts is an important and challenging problem. Recent progress on abstractive summarization in domains such as news has been driven by supervised systems trained on hundreds of thousands of news articles paired with human-written summaries. However for opinion texts, such large scale datasets are rarely available. Unsupervised methods, self-training, and few-shot learning approaches bridge that gap. In this work, we present a novel self-training approach, OpineSum, for abstractive opinion summarization. The summaries in this approach are built using a novel application of textual entailment and capture the consensus of opinions across the various reviews for an item. This method can be used to obtain silver-standard summaries on a large scale and train both unsupervised and few-shot abstractive summarization systems. OpineSum achieves state-of-the-art performance in both settings.

The applicability of computational models to the biological world is an active topic of debate. We argue that a useful path forward results from abandoning hard boundaries between categories and adopting an observer-dependent, pragmatic view. Such a view dissolves the contingent dichotomies driven by human cognitive biases (e.g., tendency to oversimplify) and prior technological limitations in favor of a more continuous, gradualist view necessitated by the study of evolution, developmental biology, and intelligent machines. Efforts to re-shape living systems for biomedical or bioengineering purposes require prediction and control of their function at multiple scales. This is challenging for many reasons, one of which is that living systems perform multiple functions in the same place at the same time. We refer to this as "polycomputing" - the ability of the same substrate to simultaneously compute different things. This ability is an important way in which living things are a kind of computer, but not the familiar, linear, deterministic kind; rather, living things are computers in the broad sense of computational materials as reported in the rapidly-growing physical computing literature. We argue that an observer-centered framework for the computations performed by evolved and designed systems will improve the understanding of meso-scale events, as it has already done at quantum and relativistic scales. Here, we review examples of biological and technological polycomputing, and develop the idea that overloading of different functions on the same hardware is an important design principle that helps understand and build both evolved and designed systems. Learning to hack existing polycomputing substrates, as well as evolve and design new ones, will have massive impacts on regenerative medicine, robotics, and computer engineering.