表示学习方法通​​常依赖于从单个角度捕获的对象的图像，这些对象使用仿射转换进行了转换。此外，自我监督的学习是代表学习的成功范式，它依赖于实例歧视和自我实践，这些歧视和自我授权并不能总是弥合从不同角度观察的相同对象观察之间的差距。从多个角度查看对象有助于对对象的整体理解，这在数据注释受到限制的情况下特别重要。在本文中，我们提出了一种方法，该方法将自我监督的学习与多人匹配技术结合在一起，并证明了其在通过机器人真空捕获的数据和嵌入式摄像机捕获的数据上学习更高质量表示的有效性。我们表明，同一对象的多个视图与各种自我监管的预处理算法相结合的可用性可以导致改进的对象分类性能，而无需额外的标签。

Lipschitz regularized f-divergences are constructed by imposing a bound on the Lipschitz constant of the discriminator in the variational representation. They interpolate between the Wasserstein metric and f-divergences and provide a flexible family of loss functions for non-absolutely continuous (e.g. empirical) distributions, possibly with heavy tails. We construct Lipschitz regularized gradient flows on the space of probability measures based on these divergences. Examples of such gradient flows are Lipschitz regularized Fokker-Planck and porous medium partial differential equations (PDEs) for the Kullback-Leibler and alpha-divergences, respectively. The regularization corresponds to imposing a Courant-Friedrichs-Lewy numerical stability condition on the PDEs. For empirical measures, the Lipschitz regularization on gradient flows induces a numerically stable transporter/discriminator particle algorithm, where the generative particles are transported along the gradient of the discriminator. The gradient structure leads to a regularized Fisher information (particle kinetic energy) used to track the convergence of the algorithm. The Lipschitz regularized discriminator can be implemented via neural network spectral normalization and the particle algorithm generates approximate samples from possibly high-dimensional distributions known only from data. Notably, our particle algorithm can generate synthetic data even in small sample size regimes. A new data processing inequality for the regularized divergence allows us to combine our particle algorithm with representation learning, e.g. autoencoder architectures. The resulting algorithm yields markedly improved generative properties in terms of efficiency and quality of the synthetic samples. From a statistical mechanics perspective the encoding can be interpreted dynamically as learning a better mobility for the generative particles.

我们的工作侧重于额外的渐变学习算法，用于在双线性零和游戏中查找纳什均衡。该方法可以正式被认为是乐观镜下降\ Cite {DBLP：Cenf / ICLR / Mertikopouloslz19}的典型方法，用于中间梯度步骤，基本上导致计算（近似）最佳反应策略先前迭代的轮廓。虽然乍一看，由于不合理的大，但是对于迭代算法，中间学习步骤，我们证明该方法保证了持续收敛到均衡。特别是，我们表明该算法首先达到$ \ eta ^ {1 / rho} $ - 近似纳什均衡，以$ \ rho> 1 $，通过减少每次迭代的kullback-leibler分歧至少$ \ omega （\ eta ^ {1+ \ frac {1} {\ rho}）$，因为足够小的学习率，$ \ eta $直到该方法成为承包地图，并收敛到确切的均衡。此外，我们对乘法权重更新方法的乐观变体进行实验比较，\ Cite {Daskalakis2019LastITERATECZ}并显示我们的算法具有显着的实际潜力，因为它在加速收敛方面提供了大量的收益。