Reference-free logged energy-oracle recovery for neural approximations of symmetric coercive variational problems: conforming Riesz reconstruction and archive-level selection
对称强制变分问题神经近似的无参考记录能量-神谕恢复:符合里泽重构与存档级选择
机构 * Laboratory for Analysis and Modeling of Systems and Decision Support (LAMSAD), Hassan 1st University of Settat(塞塔特哈桑一世大学系统与决策支持分析建模实验室) ; Al Akhawayn University in Ifrane(伊夫兰阿赫拉万大学)
专题命中 后训练与偏好优化 :post-training(abstract);分类 cs.LG
AI总结 针对对称强制变分问题的神经近似,提出无参考的记录能量神谕恢复准则,通过符合里泽监测器实现存档级选择,在扩散、弹性等问题上验证了其有效性。
Comments 35 pages, 7 figures