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…
重新审视低秩适应（LoRA）在私有LLM微调中的应用，探讨差分隐私与效率的平衡。
arXiv:2510.01137v3 Announce Type: replace Abstract: Privacy is a central concern when fine-tuning large language models (LLMs) on sensitive data, and …
面向大语言模型的高效差分隐私训练方法，提出随机裁剪机制优化DP-SGD，兼顾隐私与性能。
arXiv:2605.24879v1 Announce Type: new Abstract: Large language models (LLMs) are trained on vast datasets that may contain sensitive information. Diff…
分布式训练新突破：LOSCAR-SGD通过通信计算重叠和延迟校正，实现稀疏模型平均高效加速。
arXiv:2605.20866v1 Announce Type: new Abstract: Communication is a major bottleneck in distributed learning, especially in large-scale settings and in…
深入解读从SGD到Muon的优化器演进，以Schatten-p范数统一矩阵几何约束，为AI研究者提供理论新视角
arXiv:2605.19781v1 Announce Type: new Abstract: Modern optimizers, like Muon, impose matrix-wise geometry constraints on their updates. These matrix-w…
揭秘SGD在LLM预训练中不如Adam的根源：大有效学习率的关键作用。
arXiv:2605.17787v1 Announce Type: new Abstract: It is widely believed that stochastic gradient descent (SGD) performs significantly worse than adaptiv…