We reveal that the common eigenvector of two particles' center-of-mass coordinate and mass-weightedrelative momentum is an entangled state. Its Schmidt decomposition exhibits that the entanglement involves squeezi...We reveal that the common eigenvector of two particles' center-of-mass coordinate and mass-weightedrelative momentum is an entangled state. Its Schmidt decomposition exhibits that the entanglement involves squeezingwhich depends on the ratio of two particles' masses. The corresponding entangling operators are derived.展开更多
对于非光滑强凸问题,在线梯度下降(Online Gradient Decent,OGD)取适当步长参数可以得到对数阶后悔界.然而,这并不能使一阶随机优化算法达到最优收敛速率.为解决这一问题,研究者通常采取两种方案:其一是改进算法本身,另一种是修改算法...对于非光滑强凸问题,在线梯度下降(Online Gradient Decent,OGD)取适当步长参数可以得到对数阶后悔界.然而,这并不能使一阶随机优化算法达到最优收敛速率.为解决这一问题,研究者通常采取两种方案:其一是改进算法本身,另一种是修改算法输出方式.典型的Adam(Adaptive moment estimation)型算法SAdam(Strongly convex Adaptive moment esti⁃mation)采用了改进算法的方式,并添加了自适应步长策略和动量技巧,虽然得到更好的数据依赖的后悔界,但在随机情形仍然达不到最优.针对这个问题,本文改用加权平均的算法输出方式,并且重新设计与以往算法同阶的步长超参数,提出了一种名为WSAdam(Weighted average Strongly convex Adaptive moment estimation)的Adam型算法.证明了WSAdam达到了非光滑强凸问题的最优收敛速率.经过Reddi问题的测试和在非光滑强凸函数优化中的实验,验证了所提方法的有效性.展开更多
文摘We reveal that the common eigenvector of two particles' center-of-mass coordinate and mass-weightedrelative momentum is an entangled state. Its Schmidt decomposition exhibits that the entanglement involves squeezingwhich depends on the ratio of two particles' masses. The corresponding entangling operators are derived.
文摘对于非光滑强凸问题,在线梯度下降(Online Gradient Decent,OGD)取适当步长参数可以得到对数阶后悔界.然而,这并不能使一阶随机优化算法达到最优收敛速率.为解决这一问题,研究者通常采取两种方案:其一是改进算法本身,另一种是修改算法输出方式.典型的Adam(Adaptive moment estimation)型算法SAdam(Strongly convex Adaptive moment esti⁃mation)采用了改进算法的方式,并添加了自适应步长策略和动量技巧,虽然得到更好的数据依赖的后悔界,但在随机情形仍然达不到最优.针对这个问题,本文改用加权平均的算法输出方式,并且重新设计与以往算法同阶的步长超参数,提出了一种名为WSAdam(Weighted average Strongly convex Adaptive moment estimation)的Adam型算法.证明了WSAdam达到了非光滑强凸问题的最优收敛速率.经过Reddi问题的测试和在非光滑强凸函数优化中的实验,验证了所提方法的有效性.