在许多应用中,耗散较低但高接触面积的流体流动设备很重要。设计此类设备的众所周知的策略是多尺度拓扑优化(MTO),其中在每个离散域的每个单元格中设计了最佳的微观结构。不幸的是,MTO在计算上非常昂贵,因为在同质化过程的每个步骤中,必须对不断发展的微观结构进行均质化。作为替代方案,我们在这里提出了用于设计流体流量设备的分级多尺寸拓扑优化(GMTO)。在提出的方法中,使用了几种预选但大小的参数化和定向的微观结构来最佳填充域。 GMTO显着降低了计算,同时保留了MTO的许多好处。特别是,此处使用神经网络(NN)实施GMTO,因为:(1)可以离线执行均质化,并在优化过程中由NN使用,(2)它可以在优化过程中在微结构之间进行连续切换(3(3)(3)(3 )设计变量和计算工作的数量独立于所使用的微结构数量,(4)它支持自动分化,从而消除了手动灵敏度分析。提出了几个数值结果,以说明所提出的框架。
translated by 谷歌翻译
微观结构,即构造材料,通常是通过最大化目标(例如散装模量)的最大化,但受体积约束的影响。但是,在许多应用中,通常更适合对其他感兴趣的物理量强加约束。在本文中,我们考虑了这种广义的微结构优化问题,即任何微观结构数量,即,散装,剪切,泊松比或体积,都可以作为目标,而其余的则可以作为约束。特别是,我们在这里提出了一个神经网络(NN)框架来解决此类问题。该框架取决于微结构优化的经典密度公式,但密度场是通过NN的重量和偏见表示的。提出的NN框架的主要特征是:(1)它支持自动差异化,消除了对手动灵敏度派生的需求,(2)由于隐式过滤而不需要平滑过滤器,(3)可以轻松地将框架延伸到多个框架。 - 材料和(4)可以通过简单的后处理步骤回收高分辨率的微结构拓扑。通过各种微观结构优化问题来说明该框架。
translated by 谷歌翻译
工程设计过程通常需要优化底层几何体,同时选择合适的材料。对于某种类别的简单问题,两个是可分离的,例如,例如,可以首先选择最佳材料,然后优化几何形状。然而,一般而言,这两个不可分离。此外,材料选择的离散性质与基于梯度的几何优化不兼容,使得同时优化具有挑战性。在本文中,我们提出了使用变分性AutoEncoders(VAE)来同时优化。首先,使用数据驱动的VAE用于将离散材料数据库投影到连续和可差的潜空间上。然后将其与嵌入有限元求解器的完全连接的神经网络耦合,同时优化材料和几何形状。在优化期间利用神经网络的内置梯度优化器和背传播。使用桁架来证明所提出的框架,其中需要从数据库中选择最佳材料,同时优化桁架成员的横截面积。几个数值示例说明了所提出的框架的功效。这些实验中使用的Python代码可在Github.com/uw-ersl/matruss上获得
translated by 谷歌翻译
In nonparametric independence testing, we observe i.i.d.\ data $\{(X_i,Y_i)\}_{i=1}^n$, where $X \in \mathcal{X}, Y \in \mathcal{Y}$ lie in any general spaces, and we wish to test the null that $X$ is independent of $Y$. Modern test statistics such as the kernel Hilbert-Schmidt Independence Criterion (HSIC) and Distance Covariance (dCov) have intractable null distributions due to the degeneracy of the underlying U-statistics. Thus, in practice, one often resorts to using permutation testing, which provides a nonasymptotic guarantee at the expense of recalculating the quadratic-time statistics (say) a few hundred times. This paper provides a simple but nontrivial modification of HSIC and dCov (called xHSIC and xdCov, pronounced ``cross'' HSIC/dCov) so that they have a limiting Gaussian distribution under the null, and thus do not require permutations. This requires building on the newly developed theory of cross U-statistics by Kim and Ramdas (2020), and in particular developing several nontrivial extensions of the theory in Shekhar et al. (2022), which developed an analogous permutation-free kernel two-sample test. We show that our new tests, like the originals, are consistent against fixed alternatives, and minimax rate optimal against smooth local alternatives. Numerical simulations demonstrate that compared to the full dCov or HSIC, our variants have the same power up to a $\sqrt 2$ factor, giving practitioners a new option for large problems or data-analysis pipelines where computation, not sample size, could be the bottleneck.
translated by 谷歌翻译
Independence testing is a fundamental and classical statistical problem that has been extensively studied in the batch setting when one fixes the sample size before collecting data. However, practitioners often prefer procedures that adapt to the complexity of a problem at hand instead of setting sample size in advance. Ideally, such procedures should (a) allow stopping earlier on easy tasks (and later on harder tasks), hence making better use of available resources, and (b) continuously monitor the data and efficiently incorporate statistical evidence after collecting new data, while controlling the false alarm rate. It is well known that classical batch tests are not tailored for streaming data settings, since valid inference after data peeking requires correcting for multiple testing, but such corrections generally result in low power. In this paper, we design sequential kernelized independence tests (SKITs) that overcome such shortcomings based on the principle of testing by betting. We exemplify our broad framework using bets inspired by kernelized dependence measures such as the Hilbert-Schmidt independence criterion (HSIC) and the constrained-covariance criterion (COCO). Importantly, we also generalize the framework to non-i.i.d. time-varying settings, for which there exist no batch tests. We demonstrate the power of our approaches on both simulated and real data.
translated by 谷歌翻译
The kernel Maximum Mean Discrepancy~(MMD) is a popular multivariate distance metric between distributions that has found utility in two-sample testing. The usual kernel-MMD test statistic is a degenerate U-statistic under the null, and thus it has an intractable limiting distribution. Hence, to design a level-$\alpha$ test, one usually selects the rejection threshold as the $(1-\alpha)$-quantile of the permutation distribution. The resulting nonparametric test has finite-sample validity but suffers from large computational cost, since every permutation takes quadratic time. We propose the cross-MMD, a new quadratic-time MMD test statistic based on sample-splitting and studentization. We prove that under mild assumptions, the cross-MMD has a limiting standard Gaussian distribution under the null. Importantly, we also show that the resulting test is consistent against any fixed alternative, and when using the Gaussian kernel, it has minimax rate-optimal power against local alternatives. For large sample sizes, our new cross-MMD provides a significant speedup over the MMD, for only a slight loss in power.
translated by 谷歌翻译
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.
translated by 谷歌翻译
预先训练的大语言模型(LLM)(例如OpenAI Codex)通过从非正式自然语言(NL)意图中生成自然代码来自动化编码的重要方面。但是,生成的代码无法满足用户意图的任何正确性保证。实际上,很难定义正确性的概念,因为自然语言可能是模棱两可的,并且缺乏正式的语义。在本文中,我们通过提出测试驱动的用户形式化(TDUIF)的工作流程来解决以上问题的第一步,该工作流利用轻量级用户的反馈共同将用户的意图正式化为测试(部分规范) ),(b)生成符合正式用户意图的代码。要对算法进行可扩展的大规模自动化评估,而无需循环中的用户,我们描述了如何使用参考解决方案模拟用户与高保真性的互动。我们还描述并实施了几种算法组件(包括突变和排名一组测试)的替代实现,这些实现可用于有效解决TDUIF问题。我们已经开发了一个系统的Ticoder,该系统实现了多种解决方案来进行TDUIF,并将其对MBPP学术代码生成基准测试的相对有效性进行了比较。在MBPP上使用OpenAI Codex LLM的结果很有希望:我们的最佳算法将通行证@1代码生成准确度指标从48.39%提高到单个用户查询,最高为85.48%,最多可达55.48%,最多可提供5个用户查询。其次,我们可以生成与用户意图在1.69个用户查询中的非平凡功能单位测试,该数据集为90.40%的示例,用于此数据集。
translated by 谷歌翻译
有效的沟通需要适应与每个交流伙伴共享的特质共同基础。我们研究了这个问题的特别具有挑战性的实例化:流行的游戏dixit。我们将一轮dixit作为多代理图像参考游戏,在其中(训练有素的)扬声器模型描述了目标图像,以使一个(预审计的)侦听器模型可以从一组干扰器中正确识别它,但另一个听众无法识别它。为了适应这种设置,演讲者必须利用与不同听众共享的共同点的差异。我们表明,在这种对比性的多代理设置中,在剪辑视觉编码器和大型语言模型之间进行基于注意力的适配器会产生与上下文相关的自然语言专业化,而无需直接监督。在一系列受控的实验中,我们表明说话者可以根据各对不同听众的特质优势和劣势来适应。此外,我们显示了说话者专业化对看不见的现实世界数据的零拍传输。我们的实验为复杂的多方设置中的自适应沟通提供了一步,并突出了Dixit等游戏带来的有趣的研究挑战。我们希望我们的工作能够激发创造性的新方法,以适应预处理的模型。
translated by 谷歌翻译
视觉域的适应性(DA)试图将经过训练的模型转移到分发转移的未看到的,未标记的域,但是方法通常着重于适应卷积神经网络体系结构,并使用有监督的成像网表示。在这项工作中,我们将重点转移到将现代体系结构改编成对象识别的重点 - 越来越流行的视觉变压器(VIT)以及基于自我监督的学习(SSL)的现代预测。受到最新SSL方法的启发,该方法是基于通过掩盖或裁剪生成的部分图像输入的学习的 - 要么通过学习预测缺失的像素或学习代表性的不断增强来进行这种增强 - 我们提出了简单的两阶段适应性PACMAC自我监督VIT的算法。 PACMAC首先在汇总源和目标数据上执行内域SSL,以学习任务歧视性特征,然后探究该模型的预测一致性,这些歧视性的一致性是通过新的注意力条件掩盖策略生成的一组部分目标输入,以识别自我候选者的可靠候选者-训练。我们的简单方法导致对使用VIT和对标准对象识别基准的自我监督初始化的竞争方法的性能一致。可在https://github.com/virajprabhu/pacmac上找到代码
translated by 谷歌翻译