Deep neural networks are notorious for being sensitive to small well-chosen perturbations, and estimating the regularity of such architectures is of utmost importance for safe and robust practical applications. In this paper, we investigate one of the key characteristics to assess the regularity of such methods: the Lipschitz constant of deep learning architectures. First, we show that, even for two layer neural networks, the exact computation of this quantity is NP-hard and state-of-art methods may significantly overestimate it. Then, we both extend and improve previous estimation methods by providing AutoLip, the first generic algorithm for upper bounding the Lipschitz constant of any automatically differentiable function. We provide a power method algorithm working with automatic differentiation, allowing efficient computations even on large convolutions. Second, for sequential neural networks, we propose an improved algorithm named SeqLip that takes advantage of the linear computation graph to split the computation per pair of consecutive layers. Third we propose heuristics on SeqLip in order to tackle very large networks. Our experiments show that SeqLip can significantly improve on the existing upper bounds. Finally, we provide an implementation of AutoLip in the PyTorch environment that may be used to better estimate the robustness of a given neural network to small perturbations or regularize it using more precise Lipschitz estimations.Recently, Lipschitz continuity was used in order to improve the state-of-the-art in several deep learning topics: (1) for robust learning, avoiding adversarial attacks was achieved in [15] by constraining local Lipschitz constants in neural networks. (2) For generative models, using spectral normalization on each layer allowed [13] to successfully train a GAN on ILRSVRC2012 dataset. (3) In deep 32nd Conference on Neural Information Processing Systems (NeurIPS 2018),
translated by 谷歌翻译
图像文本匹配是在涉及对视觉和语言的共同理解的任务中发挥领导作用。在文献中,此任务通常被用作培训能够共同处理图像和文本的架构的预训练目标。但是,它具有直接的下游应用程序:跨模式检索,其中包括查找与给定查询文本或反之亦然相关的图像。解决此任务对于跨模式搜索引擎至关重要。许多最近的方法提出了针对图像文本匹配问题的有效解决方案,主要是使用最近的大型视觉语言(VL)变压器网络。但是,这些模型通常在计算上很昂贵,尤其是在推理时间。这样可以防止他们在大规模的跨模式检索场景中采用,几乎应该立即向用户提供结果。在本文中,我们建议通过提出对齐和提炼网络(Aladin)来填补有效性和效率之间的空白。阿拉丁首先通过在细粒度的图像和文本上对齐来产生高效的分数。然后,它通过提炼从细粒对齐方式获得的相关性分数来提炼共享的嵌入空间 - 可以进行有效的KNN搜索。我们在MS-Coco上取得了显着的结果,表明我们的方法可以与最先进的VL变形金刚竞争,同时快了近90倍。复制我们结果的代码可在https://github.com/mesnico/aladin上获得。
translated by 谷歌翻译
我们考虑估计与I.I.D的排名$ 1 $矩阵因素的问题。高斯,排名$ 1 $的测量值,这些测量值非线性转化和损坏。考虑到非线性的两种典型选择,我们研究了从随机初始化开始的此非convex优化问题的天然交流更新规则的收敛性能。我们通过得出确定性递归,即使在高维问题中也是准确的,我们显示出算法的样本分割版本的敏锐收敛保证。值得注意的是,虽然无限样本的种群更新是非信息性的,并提示单个步骤中的精确恢复,但算法 - 我们的确定性预测 - 从随机初始化中迅速地收敛。我们尖锐的非反应分析也暴露了此问题的其他几种细粒度,包括非线性和噪声水平如何影响收敛行为。从技术层面上讲,我们的结果可以通过证明我们的确定性递归可以通过我们的确定性顺序来预测我们的确定性序列,而当每次迭代都以$ n $观测来运行时,我们的确定性顺序可以通过$ n^{ - 1/2} $的波动。我们的技术利用了源自有关高维$ m $估计文献的遗留工具,并为通过随机数据的其他高维优化问题的随机初始化而彻底地分析了高阶迭代算法的途径。
translated by 谷歌翻译
本文分析了旋转平均问题作为相应梯度系统的潜在功能的最小化问题。这种动态系统是特殊正交组的着名kuramoto模型的一个概括(3),这被称为非阿比越士库马托模型。我们提出了一种用于寻找加权和未加权旋转平均值的新方法。为了验证我们算法的正确性,我们将仿真结果与使用真实和随机数据集进行了几何和预计平均值。特别是,我们发现我们的方法与几何平均值大致相同的结果。
translated by 谷歌翻译