在线镜像下降的近似误差竟有隐藏代价，理论推导揭示收敛性新边界，优化算法研究者必读。
arXiv:2511.22283v2 Announce Type: replace Abstract: Online mirror descent (OMD) is a fundamental algorithmic paradigm that underlies many algorithms i…
基于多层级镜像下降的稀疏训练方法，实现神经网络训练时间减少约50%
arXiv:2602.03535v2 Announce Type: replace Abstract: We introduce a dynamic sparse training algorithm based on linearized Bregman iterations / mirror d…
平均场朗之万动力学的镜像变体，为无穷宽神经网络训练提供新理论视角
arXiv:2505.02621v2 Announce Type: replace Abstract: The mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex function…