VIP内容
我们提出并分析了一种基于动量的梯度方法，用于训练具有指数尾损失(例如，指数或logistic损失)的线性分类器，它以O (1/t2)的速率最大化可分离数据的分类边缘。这与标准梯度下降的速率O(1/log(t))和标准化梯度下降的速率O(1/t)形成对比。这种基于动量的方法是通过最大边际问题的凸对偶，特别是通过将Nesterov加速度应用于这种对偶，从而在原函数中得到了一种简单而直观的方法。这种对偶观点也可以用来推导随机变量，通过对偶变量进行自适应非均匀抽样。
https://www.zhuanzhi.ai/paper/9fd848dc95d2b0a9a5da37dbbd79d4ed
成为VIP会员查看完整内容
Fast Margin Maximization via Dual Acceleration
热门内容
最新内容
最新论文
This letter addresses the 3D coverage path planning (CPP) problem for terrain reconstruction of unknown obstacle rich environments. Due to sensing limitations, the proposed method, called CT-CPP, performs layered scanning of the 3D region to collect terrain data, where the traveling sequence is optimized using the concept of a coverage tree (CT) with a TSP-inspired tree traversal strategy. The CT-CPP method is validated on a high-fidelity underwater simulator and the results are compared to an existing terrain following CPP method. The results show that CT-CPP yields significant reduction in trajectory length, energy consumption, and reconstruction error.
