1
Existential Risk from AI: An Exposition for Mathematicians
用数学家的严谨视角拆解AI存在性风险，框架清晰、论证硬核，适合理性派读者。
Article URL: https://alkjash.github.io/ai-risk/ Comments URL: https://news.ycombinator.com/item?id=49161830 Points: 1 # Comments: 0
2
Reflected diffusion, no-flux continuity equations and confined Lagrangian flows in bounded domains
从反射扩散到受限流，这篇数学论文揭示了有界域中无通量方程的新视角。
arXiv:2607.28344v1 Announce Type: cross Abstract: Motivated by marginal distribution flows of reflected diffusions in bounded domains, we investigate …
3
Layer-wise Geometric Approximation Rates for Deep Networks
从几何视角揭示深度网络逐层逼近效率，为理解深度架构优势提供新理论依据
arXiv:2604.20219v2 Announce Type: replace Abstract: Depth is widely viewed as a central contributor to the success of deep neural networks, whereas st…
4
Statistical Properties of Training & Generalization
从统计视角剖析训练与泛化机制，为机器学习理论提供严谨数学支撑。
arXiv:2606.20299v1 Announce Type: cross Abstract: Deep learning has managed to evade numerous intuitions from classical statistics to achieve unpreced…
5
When to use what Schatten-$p$ norm in deep learning?
直达 arXiv 深度学习论文页面，免费获取 Schatten-p 范数分析与 Muon 优化器的对比预印本
arXiv:2606.15268v1 Announce Type: new Abstract: Schatten-$\infty$ based optimizers such as Muon have shown promising empirical performance, but there …
6
MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysis
新基准MA-ProofBench通过两层级评估体系，系统检测LLM在数学分析定理证明中的推理边界与能力短板。
arXiv:2606.13782v1 Announce Type: new Abstract: Large Language Models (LLMs) have made notable progress in automated theorem proving, yet existing for…
7
Agreement, Diversity, and Polarization Indices for Approval Elections
批准选举中衡量共识、多样性与极化的创新指数，数学严谨且应用潜力大
arXiv:2605.14983v1 Announce Type: cross Abstract: An index is a function that given an election outputs a value between 0 and 1, indicating the extent…