The logit outputs of a feedforward neural network at initialization are conditionally Gaussian, given a random covariance matrix defined by the penultimate layer. In this work, we study the distribution of this random matrix. Recent work has shown that shaping the activation function as network depth grows large is necessary for this covariance matrix to be non-degenerate. However, the current infinite-width-style understanding of this shaping method is unsatisfactory for large depth: infinite-width analyses ignore the microscopic fluctuations from layer to layer, but these fluctuations accumulate over many layers. To overcome this shortcoming, we study the random covariance matrix in the shaped infinite-depth-and-width limit. We identify the precise scaling of the activation function necessary to arrive at a non-trivial limit, and show that the random covariance matrix is governed by a stochastic differential equation (SDE) that we call the Neural Covariance SDE. Using simulations, we show that the SDE closely matches the distribution of the random covariance matrix of finite networks. Additionally, we recover an if-and-only-if condition for exploding and vanishing norms of large shaped networks based on the activation function.

经典地，连续时间兰富文队扩散在唯一的假设下迅速迅速迅速迅速迅速，以至于$ \ PI $满足POINCAR的不平等。使用这一事实来为离散时间Langevin Monte Carlo（LMC）算法提供保证，因此由于需要与Chi Squared或R \'enyi分歧的需要，并且在很大程度上主要重点关注日志凹形目标。在这项工作中，我们为LMC提供了第一个收敛保证，假设$ \ PI $满足Lata {\ l} a - oleszkiewicz或修改的log-sobolev不等式，它在Poincar \ e和log-sobolev设置之间插值。与现有作品不同，我们的结果允许弱滑性，并且不需要凸起或耗散条件。

我们提出了一种基于langevin扩散的算法，以在球体的产物歧管上进行非凸优化和采样。在对数Sobolev不平等的情况下，我们根据Kullback-Leibler Divergence建立了有限的迭代迭代收敛到Gibbs分布的保证。我们表明，有了适当的温度选择，可以保证，次级最小值的次数差距很小，概率很高。作为一种应用，我们考虑了使用对角线约束解决半决赛程序（SDP）的burer- monteiro方法，并分析提出的langevin算法以优化非凸目标。特别是，我们为Burer建立了对数Sobolev的不平等现象 - 当没有虚假的局部最小值时，但在鞍点下，蒙蒂罗问题。结合结果，我们为SDP和最大切割问题提供了全局最佳保证。更确切地说，我们证明了Langevin算法在$ \ widetilde {\ omega}（\ epsilon^{ - 5}）$ tererations $ tererations $ \ widetilde {\ omega}（\ omega}中，具有很高的概率。

在拒绝的环境中进行搜索对于群体机器人来说是具有挑战性的，因为不允许GNSS，映射，数据共享和中央处理的帮助。但是，使用嗅觉和听觉像动物一样合作可能是改善群体合作的重要方法。在本文中，提出了一群自主机器人来探索拒绝环境的嗅觉审计算法算法（OA-BUG）。构建了一个模拟环境，以衡量OA-BUG的性能。使用OA-BUG的搜索任务覆盖范围可以达到96.93％，与类似的算法SGBA相比，最大的40.55％提高了40.55％。此外，在实际的群机器人上进行了实验，以证明OA-BUG的有效性。结果表明，OA-BUG可以在被拒绝的环境中改善群体机器人的性能。

音频命令是一种首选的沟通媒介，可将检查员保持在半自治无人机进行的民用基础设施检查环境中。为了了解一组异质和动态检查员的特定工作命令，需要为小组成本开发一个模型，并在组更改时很容易适应。本文的动机是建立一个具有股票分布的架构的多任务深度学习模型。该体系结构允许两个分类任务共享功能提取器，然后通过功能投影和协作培训在提取功能中交织在一起的特定主题和关键字特定功能。一组五个授权主题的基本模型对本研究收集的检查关键字数据集进行了培训和测试。该模型在分类任何授权检查员的关键字时达到了95.3％或更高的平均准确性。它在扬声器分类中的平均准确性为99.2％。由于该模型从合并的培训数据中学习的更丰富的关键字表示，因此将基本模型调整为新检查员只需要该检查员的少量培训数据，例如每个关键字五个话语。在验证授权检查员和76.1 \％的检测中，使用说话者分类分数进行检查员验证可以达到至少93.9％的成功率。此外，本文展示了所提出的模型对公共数据集上的大型组的适用性。本文为解决AI辅助人类机器人互动面临的挑战提供了解决方案，包括工人异质性，工人动态和工作异质性。

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。

没有发言者标签的培训扬声器 - 识别和强大的发言者验证系统仍然挑战和值得探索。在这项研究中，我们提出了一种有效的自我监督的学习框架和一种新的正规化策略，以促进自我监督的发言者代表学习。不同于基于对比的自我监督的学习方法，所提出的自我监督正则化（SSREG）专注于正数据对潜在的潜在表示之间的相似性。我们还探讨了替代在线数据增强策略对时域和频域的有效性。凭借我们强大的在线数据增强策略，所提出的SSREG显示了自我监督学习的潜力，而不使用负对对，它可以显着提高自我监督扬声器表示学习与简单的暹罗网络架构的表现。 VOXECEB数据集的综合实验表明，我们提出的自我监督方法通过增加有效的自我监督正则化和胜过其他以前的作品来获得23.4％的相对改善。

Sequence-to-sequence neural network models for generation of conversational responses tend to generate safe, commonplace responses (e.g., I don't know) regardless of the input. We suggest that the traditional objective function, i.e., the likelihood of output (response) given input (message) is unsuited to response generation tasks. Instead we propose using Maximum Mutual Information (MMI) as the objective function in neural models. Experimental results demonstrate that the proposed MMI models produce more diverse, interesting, and appropriate responses, yielding substantive gains in BLEU scores on two conversational datasets and in human evaluations. Input: What are you doing? −0.86 I don't know. −1.09 Get out of here. −1.03 I don't know! −1.09 I'm going home. −1.06 Nothing. −1.09 Oh my god! −1.09 Get out of the way. −1.10 I'm talking to you. Input: what is your name? −0.91 I don't know. ... −0.92 I don't know! −1.55 My name is Robert. −0.92 I don't know, sir. −1.58 My name is John. −0.97 Oh, my god! −1.59 My name's John. Input: How old are you? −0.79 I don't know. ... −1.06 I'm fine.−1.64 Twenty-five. −1.17 I'm all right.−1.66 Five. −1.17 I'm not sure.−1.71 Eight.

An oft-cited open problem of federated learning is the existence of data heterogeneity at the clients. One pathway to understanding the drastic accuracy drop in federated learning is by scrutinizing the behavior of the clients' deep models on data with different levels of "difficulty", which has been left unaddressed. In this paper, we investigate a different and rarely studied dimension of FL: ordered learning. Specifically, we aim to investigate how ordered learning principles can contribute to alleviating the heterogeneity effects in FL. We present theoretical analysis and conduct extensive empirical studies on the efficacy of orderings spanning three kinds of learning: curriculum, anti-curriculum, and random curriculum. We find that curriculum learning largely alleviates non-IIDness. Interestingly, the more disparate the data distributions across clients the more they benefit from ordered learning. We provide analysis explaining this phenomenon, specifically indicating how curriculum training appears to make the objective landscape progressively less convex, suggesting fast converging iterations at the beginning of the training procedure. We derive quantitative results of convergence for both convex and nonconvex objectives by modeling the curriculum training on federated devices as local SGD with locally biased stochastic gradients. Also, inspired by ordered learning, we propose a novel client selection technique that benefits from the real-world disparity in the clients. Our proposed approach to client selection has a synergic effect when applied together with ordered learning in FL.

Nine language-vision AI models trained on web scrapes with the Contrastive Language-Image Pretraining (CLIP) objective are evaluated for evidence of a bias studied by psychologists: the sexual objectification of girls and women, which occurs when a person's human characteristics are disregarded and the person is treated as a body or a collection of body parts. A first experiment uses standardized images of women from the Sexual OBjectification and EMotion Database, and finds that, commensurate with prior research in psychology, human characteristics are disassociated from images of objectified women: the model's recognition of emotional state is mediated by whether the subject is fully or partially clothed. Embedding association tests (EATs) return significant effect sizes for both anger (d >.8) and sadness (d >.5). A second experiment measures the effect in a representative application: an automatic image captioner (Antarctic Captions) includes words denoting emotion less than 50% as often for images of partially clothed women than for images of fully clothed women. A third experiment finds that images of female professionals (scientists, doctors, executives) are likely to be associated with sexual descriptions relative to images of male professionals. A fourth experiment shows that a prompt of "a [age] year old girl" generates sexualized images (as determined by an NSFW classifier) up to 73% of the time for VQGAN-CLIP (age 17), and up to 40% of the time for Stable Diffusion (ages 14 and 18); the corresponding rate for boys never surpasses 9%. The evidence indicates that language-vision AI models trained on automatically collected web scrapes learn biases of sexual objectification, which propagate to downstream applications.