双智能体驱动AI，革新凸松弛发现路径，优化理论前沿突破。
arXiv:2606.31182v1 Announce Type: new Abstract: Recent work shows that LLM agents can improve sharp-constant inequalities by searching for extremal co…
AI最终破解了最古老随机梯度下降算法的复杂度难题，数学理论迎来新突破。
arXiv:2606.29593v1 Announce Type: new Abstract: In 1937, Stefan Kaczmarz proposed a simple algorithm for solving systems of linear equations. This alg…
联邦学习场景中，理论推导出非退化条件下带宽-准确率最优匹配率与最优分配策略，为异构带宽蒸馏提供严谨边界。
arXiv:2605.29642v1 Announce Type: cross Abstract: In federated language modeling, $K$ nodes each hold $n$ samples but cannot pool data or exchange ful…
从热力学视角揭示训练算法的不可逆本质，为理解深度学习优化过程提供全新理论框架。
arXiv:2605.21933v1 Announce Type: cross Abstract: The training algorithms for AI systems all introduce far-from-equilibrium dynamical processes, and u…