arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1805.09545math.OCcs.NEstat.ML
收藏

基于最优输运的过参数模型梯度下降的整体收敛

On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport

Lenaic Chizat, Francis Bach

摘要:

机器学习和信号处理中的许多任务可以通过最小化度量的凸函数来解决。这包括稀疏尖峰反卷积或训练具有单个隐藏层的神经网络。对于这些问题,我们研究了一个简单的最小化方法:未知的测量被离散成一个粒子的混合物和连续时间梯度下降进行他们的权重和位置。这是一个理想化的通常方式训练神经网络与一个大的隐藏层。我们表明,当初始化正确,在许多粒子的限制,这个梯度流,虽然非凸,收敛到全局极小。证明涉及沃瑟斯坦梯度流,一个副产品的最优输运理论。数值实验表明,这种渐近行为已经在合理数量的粒子,甚至在高维发挥作用。

英文摘要:

Many tasks in machine learning and signal processing can be solved by minimizing a convex function of a measure. This includes sparse spikes deconvolution or training a neural network with a single hidden layer. For these problems, we study a simple minimization method: the unknown measure is discretized into a mixture of particles and a continuous-time gradient descent is performed on their weights and positions. This is an idealization of the usual way to train neural networks with a large hidden layer. We show that, when initialized correctly and in the many-particle limit, this gradient flow, although non-convex, converges to global minimizers. The proof involves Wasserstein gradient flows, a by-product of optimal transport theory. Numerical experiments show that this asymptotic behavior is already at play for a reasonable number of particles, even in high dimension.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑