系统梳理深度学习理论，揭示从近似到涌现的演进逻辑。
From Approximation to Emergence: A Theory of Deep Learning
- 构建统一理论框架，贯通近似、优化与泛化等经典理论
- 揭示大规模模型中鲁棒性、生成能力等现象的形成机制
- 适合研究者和高阶学习者，理解深度学习本质演化
深度学习已超越单一数学解释。《从近似到涌现：深度学习理论》提出一个以证明为导向的统一理论体系，追溯从经典近似、优化与泛化理论，到现代过参数化、鲁棒性、生成建模、Transformer、上下文学习、缩放定律、可解释性、对齐及涌现等机制的演进路径。本书不孤立呈现成果，而是通过分析每种理论所控制的对象、有效假设及其未解问题，将广泛文献整合为连贯的研究叙事。面向研究人员、研究生及具备数学基础的实践者，本书提供当前深度学习理论的严谨图谱：强大而不完备，日益聚焦于规模、数据、架构与训练如何共同催生学习机制。
原文摘要 · Abstract (English)
Deep learning has outgrown any single mathematical explanation. From Approximation to Emergence develops a unified, proof-oriented account of modern deep learning theory, tracing a path from the classical foundations of approximation, optimization, and generalization to the contemporary mechanisms of overparameterization, robustness, generative modeling, transformers, in-context learning, scaling laws, interpretability, alignment, and emergence. Rather than presenting isolated results, the book organizes a broad literature into a coherent research narrative: each theory is examined through the object it controls, the assumptions that make it valid, and the phenomena it leaves unexplained. Written for researchers, graduate students, and mathematically trained practitioners, this monograph offers a rigorous map of deep learning theory as it stands today: powerful, incomplete, and increasingly centered on the question of how learned mechanisms arise from scale, data, architecture, and training.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。