math-skill 2.1.0 → 3.0.0

package/knowledge-base/overview.en.md

@@ -1,228 +1,39 @@
-# Mathematical Knowledge System Overview
+# Knowledge Base Navigation
 
-## Overview
+> This file is the v3 knowledge base index, helping you find specific knowledge cards from problem types.
 
-The mathematical knowledge system is the structured framework of the discipline of mathematics, spanning from foundational concepts to cutting-edge subfields. It describes not only the hierarchical relationships among sub-disciplines, but also how mathematical methods complement and synergize across different problem domains.
+## Knowledge Base Structure
 
-This overview is designed to help you:
+The knowledge base is organized by mathematical domain, with 7 domains and 31 knowledge cards. Each card contains: minimal definition, core formulas, applicable problems, AI design translation, engineering feasibility, risks and failure conditions.
 
-- Quickly locate the discipline and method area to which a mathematical problem belongs;
-- Understand the correspondence between the 16 thinking weapons in this project (15 weapons + math-research-activator) and mathematical sub-disciplines;
-- Build a holistic understanding from problem to tool, from concept to application.
+| Domain | Directory | Cards | Typical Applications |
+|--------|-----------|-------|---------------------|
+| Matrix Analysis | `matrix-analysis/` | projection, spectral-decomposition, low-rank-approximation, positive-semidefinite, matrix-perturbation | LoRA, spectral normalization, condition number monitoring |
+| Optimization | `optimization/` | lagrangian-duality, convex-optimization, constrained-optimization, riemannian-optimization, proximal-method | GAN minimax, weight constraints, Muon optimizer |
+| Differential Geometry | `differential-geometry/` | manifold, tangent-space, metric-tensor, geodesic, curvature, connection | Natural gradient, manifold optimization, K-FAC |
+| Lie Theory | `lie-theory/` | group-action, lie-group, lie-algebra, representation, equivariance | Equivariant networks, SO(3) parameterization, spherical harmonics |
+| Topology | `topology/` | persistent-homology, euler-characteristic, fundamental-group | Topological regularization, latent space monitoring |
+| Probability & Information | `probability/` | concentration-inequality, entropy, kl-divergence, information-bottleneck, fisher-information | VAE, knowledge distillation, generalization bounds |
+| Information Geometry | `information-geometry/` | natural-gradient, fisher-metric | Natural gradient descent, Fisher-Rao metric |
 
-The development of mathematics has been jointly driven by logical reasoning, scientific needs, and cross-disciplinary applications.
+## From Problem to Knowledge Card
 
-## 1. The Three Foundational Pillars of Mathematics
+| Problem Type | Recommended Cards |
+|-------------|-------------------|
+| Need dimensionality reduction/compression | low-rank-approximation, projection |
+| Need constrained optimization | constrained-optimization, lagrangian-duality |
+| Need equivariance/symmetry | group-action, equivariance, representation |
+| Need stable training | matrix-perturbation, positive-semidefinite, fisher-information |
+| Need manifold parameterization | manifold, riemannian-optimization, tangent-space |
+| Need information compression | information-bottleneck, entropy, kl-divergence |
+| Need topological regularization | persistent-homology, euler-characteristic |
 
-The edifice of modern mathematics is built on **set theory** and **mathematical logic**. The three foundational disciplines are:
+## Relationship to Thinking Lenses
 
-### Algebra
+Thinking lenses (`../../lenses/`) handle "what perspective to use"; the knowledge base provides "concrete mathematical tools." Typical chain:
 
-The study of numbers, structures, relationships, and symbolic operations.
+```
+Lens diagnosis → Knowledge card provides tools → Design pattern translates to AI module
+```
 
-| Level | Content | Core Concepts |
-|-------|---------|--------------|
-| Elementary Algebra | Equations, inequalities, polynomial operations | Variables, identities, operation laws |
-| Advanced Algebra (Linear Algebra) | Vector spaces, linear transformations, matrices | Linear spaces, bases, dimension, eigenvalues |
-| Abstract Algebra | Groups, rings, fields | Algebraic structures, homomorphisms, isomorphisms |
-| Category Theory | Abstract theory of objects and morphisms | Functors, natural transformations, universal properties |
-
-### Geometry
-
-The study of space, shape, structure, and their relationships.
-
-| Level | Content | Core Concepts |
-|-------|---------|--------------|
-| Euclidean Geometry | Plane and solid geometry | Points, lines, planes, angles, distances |
-| Analytic Geometry | Studying geometry via algebraic methods | Coordinate systems, equations, curves |
-| Non-Euclidean Geometry | Geometries with modified parallel postulates | Hyperbolic geometry, elliptic geometry |
-| Differential Geometry | Studying geometry via calculus | Curvature, geodesics, manifolds |
-| Fractal Geometry | Self-similar geometric structures | Fractal dimension, iterated function systems |
-
-### Analysis
-
-The study of functions, limits, continuity, differentiation, and integration.
-
-| Level | Content | Core Concepts |
-|-------|---------|--------------|
-| Calculus | Limits, derivatives, integrals | Continuity, differentiability, integrability |
-| Mathematical Analysis | Rigorous limit theory | $\varepsilon$-$\delta$ language, uniform convergence |
-| Real Analysis | Measure theory, Lebesgue integration | Measure spaces, $L^p$ spaces |
-| Complex Analysis | Theory of complex functions | Analytic functions, residues, conformal mappings |
-| Functional Analysis | Analysis on infinite-dimensional spaces | Banach spaces, Hilbert spaces, operators |
-| Differential Equations | ODEs and PDEs | Existence, uniqueness, stability, numerical methods |
-
-## 2. Major Branches
-
-### 1. Number Theory
-
-The study of integer properties, such as prime distribution, congruences, and Diophantine equations.
-
-- **Elementary Number Theory**: Divisibility, congruences, primes
-- **Analytic Number Theory**: Using analytical methods for number-theoretic problems (e.g., the Prime Number Theorem)
-- **Algebraic Number Theory**: Using algebraic methods for number-theoretic problems (e.g., algebraic number fields)
-- **Geometric Number Theory**: Using geometric methods for number-theoretic problems
-
-### 2. Probability & Statistics
-
-The study of random phenomena and data analysis, widely applied in finance, biology, and social sciences. Corresponding thinking weapons: **Probability & Statistics**, **Information Theory**, **Causal Inference**.
-
-- **Probability Theory**: Random variables, distributions, limit theorems → See **Probability & Statistics** (Kolmogorov axioms)
-- **Mathematical Statistics**: Parameter estimation, hypothesis testing, regression analysis → See **Probability & Statistics** (regression modeling, experimental design)
-- **Stochastic Processes**: Markov chains, Brownian motion, martingale theory
-- **Bayesian Statistics**: Priors, posteriors, MCMC → See **Information Theory** (maximum entropy principle)
-
-### 3. Topology
-
-The study of invariant properties of spaces under continuous deformation. Corresponding thinking weapon: **Topological Thinking**.
-
-- **Point-Set Topology**: Open sets, closed sets, connectedness, compactness → See **Symmetry & Invariance** (invariant perspective)
-- **Algebraic Topology**: Homotopy, homology, cohomology → See **Topological Thinking** (fundamental group, Betti numbers)
-- **Differential Topology**: Manifolds, tangent spaces, differential forms
-
-### 4. Discrete Mathematics
-
-Set theory, graph theory, mathematical logic, etc. — the mathematical foundation of computer science. Corresponding thinking weapons: **Algorithmic & Computational Thinking**, **Discrete & Combinatorial Thinking**.
-
-- **Set Theory**: Sets, relations, functions, cardinality, ordinals
-- **Graph Theory**: Graphs, paths, connectivity, coloring, network flows
-- **Mathematical Logic**: Propositional logic, predicate logic, computability → See **Axiomatic Thinking**, **Logical Deduction**
-- **Combinatorics**: Counting, permutations and combinations, generating functions → See **Discrete & Combinatorial Thinking**
-- **Algorithms & Complexity**: Sorting, searching, P/NP, decidability → See **Algorithmic & Computational Thinking**
-
-### 5. Applied Mathematics Branches
-
-Applying mathematical methods to real-world problems. Corresponding thinking weapons: **Optimization**, **Information Theory**, **Game Theory**, **Algorithmic & Computational Thinking**, **Causal Inference**.
-
-- **Operations Research**: Linear programming, integer programming, dynamic programming, queueing theory → See **Optimization** (LP/IP/DP taxonomy), **Algorithmic & Computational Thinking** (solution algorithms)
-- **Control Theory**: System control, optimal control, robust control → See **Optimization** (optimal control as variational optimization)
-- **Information Theory**: Entropy, channel capacity, data compression, coding theory → See **Information Theory** (Shannon entropy, coding theorems)
-- **Game Theory**: Strategic interaction, equilibrium analysis, mechanism design → See **Game Theory** (Nash equilibrium, minimax)
-- **Causal Inference**: Causal graph models, intervention analysis, counterfactual reasoning → See **Causal Inference** (DAGs, do-calculus)
-- **Financial Mathematics**: Option pricing, risk management, stochastic calculus → See **Modeling** (Black-Scholes), **Probability & Statistics**
-- **Computational Mathematics**: Numerical analysis, finite elements, Monte Carlo methods → See **Algorithmic & Computational Thinking** (numerical algorithms)
-- **Mathematical Foundations of Machine Learning**: Optimization, statistical learning theory, kernel methods → See **Optimization**, **Probability & Statistics**, **Information Theory** (MDL/AIC)
-
-## 3. Hierarchical Structure of the Knowledge System
-
-From a learning-path perspective, mathematical knowledge can be organized into levels:
-
-### Foundation Level
-
-Number sense, logic and classification, arithmetic, and basic geometry.
-
-- Concepts and operations of numbers
-- Basic logical reasoning
-- Arithmetic operations (addition, subtraction, multiplication, division)
-- Basic geometric shapes and properties
-
-### Algebra Level
-
-Variables, equations, functions, geometric proofs.
-
-- Algebraic expressions and equations
-- Function concepts and basic function families
-- Plane geometry proofs
-- Vectors and coordinates
-
-### Synthesis Level
-
-Functions and derivatives, calculus, sequences, solid geometry, advanced probability and statistics.
-
-- Limits and continuity
-- Differentiation and integration
-- Sequences and series
-- Solid geometry
-- Probability distributions and statistical inference
-
-### Frontier Level
-
-Mathematical analysis, advanced algebra, analytic/differential geometry, number theory, topology, etc.
-
-- Rigorous analytical theory ($\varepsilon$-$\delta$)
-- Abstract algebraic structures (groups, rings, fields)
-- Manifolds and differential geometry
-- Algebraic/analytic number theory
-- Point-set/algebraic topology
-- Functional analysis and operator theory
-
-## 4. Levels of Mathematical Thinking Methods
-
-| Level | Thinking Method | Description |
-|-------|----------------|-------------|
-| Foundation | Logical deduction, inductive analogy | The basis of all mathematical thinking |
-| Method | Axiomatization, abstraction, modeling | Methods for constructing mathematical theories |
-| Tool | Optimization, transformation, probability & statistics | Tools for solving concrete problems |
-| Extension | Algorithms & computation, information theory, game theory, causal inference | Tools applied to computation, information, interaction, and causation |
-| Philosophy | Symmetry & invariance, topological thinking, discrete & combinatorial thinking | Philosophical perspectives for understanding structure and essence |
-
-## 5. Connections Between Mathematics and Other Disciplines
-
-| Discipline | Mathematical Tools Used | Typical Applications |
-|-----------|------------------------|---------------------|
-| Physics | Calculus, linear algebra, group theory | Mechanics, quantum mechanics, relativity |
-| Computer Science | Discrete mathematics, graph theory, probability | Algorithm analysis, cryptography, AI |
-| Economics | Optimization, game theory, differential equations | Market equilibrium, pricing models |
-| Biology | Differential equations, statistics, graph theory | Population dynamics, systems biology |
-| Engineering | Differential equations, Fourier analysis, numerical methods | Control systems, signal processing |
-| Social Sciences | Statistics, game theory, network analysis | Social networks, decision analysis |
-
-## 6. Mapping Thinking Weapons to Mathematical Branches
-
-The 16 thinking weapons in this project (15 specialized weapons + 1 math-research-activator auto-trigger entry point) do not exist in isolation; they form a complementary toolkit with mathematical branches. Below is a simplified mapping to help you find suitable mathematical methods directly from problem types. v2 also includes `references/books/*.md` × 7 volumes covering algebraic geometry / differential geometry / Lie theory / abstract algebra / matrix analysis / optimization / manifolds and other modern mathematical structures, activated on demand into algorithm design (see README "Three-Layer Progressive Disclosure").
-
-| Thinking Weapon | Corresponding Mathematical Branch | Typical Methods / Concepts |
-|----------------|----------------------------------|---------------------------|
-| 🧭 Math Research Activator | Meta-cognition, problem classification, modern math mapping | Diagnosis → Mapping → Routing → GPU Filtering, dual acceptance gates |
-| 📐 Axiomatic Thinking | Mathematical logic, set theory | Axiomatic systems, formal languages, consistency, independence |
-| 🧩 Abstraction | Algebra, category theory, topology | Abstract structures, isomorphisms, universal properties |
-| 🧠 Logical Deduction | Mathematical logic, proof theory | Propositional logic, predicate logic, inference rules |
-| 🌉 Modeling | Applied mathematics, statistics | Equation-based modeling, dimensional analysis, validation |
-| ⚖️ Optimization | Optimization theory, operations research | Convex optimization, KKT conditions, dynamic programming |
-| 🎲 Probability & Statistics | Probability theory, mathematical statistics | Random variables, hypothesis testing, regression analysis |
-| 🔄 Transformation | Analysis, generating functions | Fourier, Laplace, algebraic transformations |
-| ⚛️ Symmetry & Invariance | Group theory, geometry | Group actions, invariants, quotient spaces |
-| 📈 Induction & Analogy | Elementary mathematics, number theory | Inductive proofs, analogical reasoning, pattern recognition |
-| 🖥️ Algorithmic & Computational Thinking | Computation theory, discrete mathematics | Complexity, computability, algorithm paradigms |
-| 📡 Information Theory | Information theory, statistical learning | Entropy, mutual information, coding limits |
-| 🎯 Game Theory | Mathematical economics, mechanism design | Nash equilibrium, incentive compatibility, optimal strategy |
-| 🔗 Causal Inference | Causal inference, statistics | DAGs, do-calculus, intervention analysis |
-| 🌀 Topological Thinking | Topology, algebraic topology | Homotopy, homology, topological invariants |
-| 🧮 Discrete & Combinatorial Thinking | Combinatorics, graph theory | Pigeonhole principle, generating functions, enumeration |
-
-## 7. How to Choose a Thinking Weapon
-
-When facing a problem, the most important first step is not "analyze hard," but "choose the right tool." Here is a selection guide:
-
-### Quick Selection Guide
-
-| Core Problem Characteristic | Most Likely Suitable Thinking Weapon |
-|----------------------------|-------------------------------------|
-| Multi-party interaction; my optimum depends on others | 🎯 Game Theory |
-| Uncertainty / randomness | 🎲 Probability & Statistics |
-| Optimal choice under constraints | ⚖️ Optimization |
-| Difficult to handle from current perspective | 🔄 Transformation |
-| Need to extract essential structure | 🧩 Abstraction |
-| Need rigorous reasoning and verification | 🧠 Logical Deduction |
-| Need to discover patterns from experience | 📈 Induction & Analogy |
-| Need to build a predictive model | 🌉 Modeling |
-| Invariance amid change | ⚛️ Symmetry & Invariance |
-| Need executable steps | 🖥️ Algorithmic & Computational Thinking |
-| Counting / structure over finite objects | 🧮 Discrete & Combinatorial Thinking |
-
-### Using the Activator
-
-If you are unsure which tool to use, simply invoke the math-research-activator via the `/ask` command. It will diagnose the problem, map to modern mathematical structures, recommend the 1–3 most suitable thinking weapons, and perform GPU feasibility filtering. When algorithm / kernel / model code appears in the workspace, the activator will also intervene automatically.
-
-### Path
-
-v2 has removed the "research / life dual-path" and unified into a single research / algorithm path: preserving complete mathematical notation and derivations, and enforcing the GPU 8-dimension gate when used for algorithm / operator design.
-
-## 8. How to Use This Overview
-
-- Start from the problem characteristics: determine whether it is "structural," "dynamic," "stochastic," "interactive," or "countable."
-- Consult the Quick Selection Guide or use the `/ask` command to find the closest thinking weapon.
-- Combined with the "Hierarchical Structure of the Knowledge System," judge whether the current problem is better suited to foundational approaches or frontier methods.
-- If the problem spans multiple categories, invoke multiple thinking weapons simultaneously — e.g., "Modeling + Optimization," "Probability + Causation," "Abstraction + Algorithms."
-- For algorithm / operator design problems, let the activator transfer modern mathematical structures (algebraic geometry / Lie theory / topology, etc.) into the design and pass them through the GPU 8-dimension gate.
-- When studying or reading literature, use this overview as an organizing framework to place scattered concepts into a unified knowledge map.
+For deeper study, `../../references/books/*.md` provides 7 book distillations.

package/knowledge-base/overview.md

@@ -1,230 +1,39 @@
-> **语言路由**：若用户消息为英文，请读取并遵循同目录下的 `overview.en.md`。
+# 数学知识库导航 / Knowledge Base Navigation
 
-# 数学知识体系概述 / Mathematical Knowledge System Overview
+> 本文件是 v3 知识库的索引，帮助你从问题类型找到具体的知识卡片。
 
-## 概述
+## 知识库结构
 
-数学知识体系是数学学科的结构化框架，涵盖从基础概念到前沿分支的完整内容。它不仅描述学科之间的层次关系，也呈现出数学方法如何在不同问题域中互补与协同。
+知识库按数学领域组织，共 7 个领域、31 张知识卡片。每张卡片包含：最小定义、核心公式、适用问题、AI 设计翻译、工程可行性、风险与失效条件。
 
-本概述旨在帮助你：
+| 领域 | 目录 | 卡片 | 典型应用 |
+|------|------|------|---------|
+| 矩阵分析 | `matrix-analysis/` | projection, spectral-decomposition, low-rank-approximation, positive-semidefinite, matrix-perturbation | LoRA、谱归一化、条件数监控 |
+| 最优化 | `optimization/` | lagrangian-duality, convex-optimization, constrained-optimization, riemannian-optimization, proximal-method | GAN minimax、权重约束、Muon 优化器 |
+| 微分几何 | `differential-geometry/` | manifold, tangent-space, metric-tensor, geodesic, curvature, connection | 自然梯度、流形优化、K-FAC |
+| 李理论 | `lie-theory/` | group-action, lie-group, lie-algebra, representation, equivariance | 等变网络、SO(3) 参数化、球谐特征 |
+| 拓扑 | `topology/` | persistent-homology, euler-characteristic, fundamental-group | 拓扑正则、隐空间监控 |
+| 概率与信息 | `probability/` | concentration-inequality, entropy, kl-divergence, information-bottleneck, fisher-information | VAE、知识蒸馏、泛化界 |
+| 信息几何 | `information-geometry/` | natural-gradient, fisher-metric | 自然梯度下降、Fisher-Rao 度量 |
 
-- 快速定位数学问题所属的学科与方法领域；
-- 理解本项目 16 种思想武器（15 武器 + math-research-activator）与数学分支之间的对应关系；
-- 形成从问题到工具、从概念到应用的整体认知。
+## 从问题找知识卡
 
-数学的发展受到逻辑推理、科学需求和交叉应用的共同推动。
+| 问题类型 | 推荐知识卡 |
+|---------|-----------|
+| 需要降维/压缩 | low-rank-approximation, projection |
+| 需要约束优化 | constrained-optimization, lagrangian-duality |
+| 需要等变/对称 | group-action, equivariance, representation |
+| 需要稳定训练 | matrix-perturbation, positive-semidefinite, fisher-information |
+| 需要流形参数化 | manifold, riemannian-optimization, tangent-space |
+| 需要信息压缩 | information-bottleneck, entropy, kl-divergence |
+| 需要拓扑正则 | persistent-homology, euler-characteristic |
 
-## 一、数学体系的三大基础支柱
+## 与思想透镜的关系
 
-现代数学大厦建立在**集合论**和**数理逻辑**基础上，三大基础学科是：
+思想透镜（`../../lenses/`）负责"用什么视角看问题"，知识库负责"提供具体数学工具"。典型链路：
 
-### 代数学（Algebra）
+```
+透镜诊断 → 知识卡片提供工具 → 设计模式翻译成 AI 模块
+```
 
-研究数、结构、关系和符号运算。
-
-| 层次 | 内容 | 核心概念 |
-|------|------|---------|
-| 初等代数 | 方程、不等式、多项式运算 | 变量、等式、运算律 |
-| 高等代数（线性代数） | 向量空间、线性变换、矩阵 | 线性空间、基、维数、特征值 |
-| 抽象代数 | 群、环、域 | 代数结构、同态、同构 |
-| 范畴论 | 对象与态射的抽象理论 | 函子、自然变换、泛性质 |
-
-### 几何学（Geometry）
-
-研究空间、形状、结构及其关系。
-
-| 层次 | 内容 | 核心概念 |
-|------|------|---------|
-| 欧几里得几何 | 平面与立体几何 | 点、线、面、角、距离 |
-| 解析几何 | 用代数方法研究几何 | 坐标系、方程、曲线 |
-| 非欧几何 | 改变平行公理的几何 | 双曲几何、椭圆几何 |
-| 微分几何 | 用微积分研究几何 | 曲率、测地线、流形 |
-| 分形几何 | 自相似的几何结构 | 分形维数、迭代函数系统 |
-
-### 分析学（Analysis）
-
-研究函数、极限、连续、微分、积分等。
-
-| 层次 | 内容 | 核心概念 |
-|------|------|---------|
-| 微积分 | 极限、导数、积分 | 连续、可微、可积 |
-| 数学分析 | 严格的极限理论 | ε-δ语言、一致收敛 |
-| 实分析 | 测度论、Lebesgue 积分 | 测度空间、L^p 空间 |
-| 复分析 | 复变函数理论 | 解析函数、留数、共形映射 |
-| 泛函分析 | 无限维空间上的分析 | Banach 空间、Hilbert 空间、算子 |
-| 微分方程 | ODE 与 PDE | 存在唯一性、稳定性、数值解法 |
-
-## 二、主要分支
-
-### 1. 数论（Number Theory）
-
-研究整数性质，如素数分布、同余、丢番图方程等。
-
-- **初等数论**：整除、同余、素数
-- **解析数论**：用分析方法研究数论问题（如素数定理）
-- **代数数论**：用代数方法研究数论问题（如代数数域）
-- **几何数论**：用几何方法研究数论问题
-
-### 2. 概率论与数理统计（Probability & Statistics）
-
-研究随机现象和数据分析，广泛应用于金融、生物、社会科学等。对应思想武器：**概率与统计**、**信息论思想**、**因果推断思想**。
-
-- **概率论**：随机变量、分布、极限定理 → 详见 **概率与统计**（Kolmogorov 公理）
-- **数理统计**：参数估计、假设检验、回归分析 → 详见 **概率与统计**（回归建模、实验设计）
-- **随机过程**：马尔可夫链、布朗运动、鞅论
-- **贝叶斯统计**：先验、后验、MCMC → 详见 **信息论思想**（最大熵原则）
-
-### 3. 拓扑学（Topology）
-
-研究空间在连续变形下的不变性质。对应思想武器：**拓扑思想**。
-
-- **点集拓扑**：开集、闭集、连通性、紧致性 → 详见 **对称与不变性**（不变量视角）
-- **代数拓扑**：同伦、同调、上同调 → 详见 **拓扑思想**（基本群、Betti 数）
-- **微分拓扑**：流形、切空间、微分形式
-
-### 4. 离散数学（Discrete Mathematics）
-
-集合论、图论、数理逻辑等，是计算机科学的数学基础。对应思想武器：**算法与计算思想**、**离散与组合思想**。
-
-- **集合论**：集合、关系、函数、基数、序数
-- **图论**：图、路径、连通性、着色、网络流
-- **数理逻辑**：命题逻辑、谓词逻辑、可计算性 → 详见 **公理化思想**、**逻辑演绎**
-- **组合数学**：计数、排列组合、生成函数 → 详见 **离散与组合思想**
-- **算法与复杂度**：排序、搜索、P/NP、可判定性 → 详见 **算法与计算思想**
-
-### 5. 应用数学分支
-
-将数学方法应用于实际问题。对应思想武器：**优化思想**、**信息论思想**、**博弈论思想**、**算法与计算思想**、**因果推断思想**。
-
-- **运筹学**：线性规划、整数规划、动态规划、排队论 → 详见 **优化思想**（LP/IP/DP 分类）、**算法与计算思想**（求解算法）
-- **控制理论**：系统控制、最优控制、鲁棒控制 → 详见 **优化思想**（最优控制即变分优化）
-- **信息论**：熵、信道容量、数据压缩、编码理论 → 详见 **信息论思想**（Shannon 熵、编码定理）
-- **博弈论**：策略互动、均衡分析、机制设计 → 详见 **博弈论思想**（Nash 均衡、minimax）
-- **因果推断**：因果图模型、干预分析、反事实推理 → 详见 **因果推断思想**（DAG、do 算子）
-- **金融数学**：期权定价、风险管理、随机微积分 → 详见 **建模思想**（Black-Scholes）、**概率与统计**
-- **计算数学**：数值分析、有限元、蒙特卡洛方法 → 详见 **算法与计算思想**（数值算法）
-- **机器学习数学基础**：优化、统计学习理论、核方法 → 详见 **优化思想**、**概率与统计**、**信息论思想**（MDL/AIC）
-
-## 三、知识体系的层次结构
-
-从学习路径看，数学知识可分层次：
-
-### 地基层
-
-数感、逻辑与分类、算术与基础几何。
-
-- 数的概念与运算
-- 基本逻辑推理
-- 算术运算（加减乘除）
-- 基础几何图形与性质
-
-### 代数层
-
-变量、方程、函数、几何证明。
-
-- 代数表达式与方程
-- 函数概念与基本函数族
-- 平面几何证明
-- 向量与坐标
-
-### 综合层
-
-函数与导数、微积分、数列、立体几何、概率统计深化。
-
-- 极限与连续
-- 微分与积分
-- 数列与级数
-- 立体几何
-- 概率分布与统计推断
-
-### 前沿层
-
-数学分析、高等代数、解析/微分几何、数论、拓扑学等。
-
-- 严格的分析理论（ε-δ）
-- 抽象代数结构（群环域）
-- 流形与微分几何
-- 代数/解析数论
-- 点集/代数拓扑
-- 泛函分析与算子理论
-
-## 四、数学思想方法的层次
-
-| 层次 | 思想方法 | 说明 |
-|------|---------|------|
-| 基础层 | 逻辑演绎、归纳类比 | 所有数学思维的基础 |
-| 方法层 | 公理化、抽象化、建模 | 构建数学理论的方法 |
-| 工具层 | 优化、变换、概率统计 | 解决具体问题的工具 |
-| 拓展层 | 算法与计算、信息论、博弈论、因果推断 | 应用于计算、信息、互动和因果的工具 |
-| 哲学层 | 对称不变性、拓扑思想、离散组合 | 理解结构与本质的哲学视角 |
-
-## 五、数学与其他学科的联系
-
-| 学科 | 使用的数学工具 | 典型应用 |
-|------|--------------|---------|
-| 物理学 | 微积分、线性代数、群论 | 力学、量子力学、相对论 |
-| 计算机科学 | 离散数学、图论、概率 | 算法分析、密码学、AI |
-| 经济学 | 优化、博弈论、微分方程 | 市场均衡、定价模型 |
-| 生物学 | 微分方程、统计、图论 | 种群动力学、系统生物学 |
-| 工程学 | 微分方程、傅里叶分析、数值方法 | 控制系统、信号处理 |
-| 社会科学 | 统计、博弈论、网络分析 | 社会网络、决策分析 |
-
-## 六、思维武器与数学分支的映射
-
-本项目的 16 种思想武器（15 种专业武器 + 1 个 math-research-activator 自动触发入口）不是孤立存在的，它们与数学分支形成了互补的工具集。下面展示一个简化映射，帮助你从问题类型直接找到适合的数学方法。v2 另有 `references/books/*.md` × 7 把代数几何 / 微分几何 / 李理论 / 抽象代数 / 矩阵分析 / 最优化 / 流形等现代数学结构按需激活进算法设计（见 README「三层渐进式披露」）。
-
-| 思维武器 | 对应数学分支 | 典型方法/概念 |
-|---------|-------------|--------------|
-| 🧭 数学研究激活器 | 元认知、问题分类、现代数学映射 | 诊断→映射→路由→GPU 筛选、双验收门 |
-| 📐 公理化思想 | 数理逻辑、集合论 | 公理体系、形式语言、相容性、独立性 |
-| 🧩 抽象化思想 | 代数、范畴论、拓扑学 | 抽象结构、同构、泛性质 |
-| 🧠 逻辑演绎 | 数理逻辑、证明论 | 命题逻辑、谓词逻辑、推理规则 |
-| 🌉 建模思想 | 应用数学、统计 | 方程建模、量纲分析、验证 |
-| ⚖️ 优化思想 | 最优化、运筹学 | 凸优化、KKT、动态规划 |
-| 🎲 概率与统计 | 概率论、数理统计 | 随机变量、假设检验、回归分析 |
-| 🔄 变换思想 | 分析学、生成函数 | 傅里叶、拉普拉斯、代数变换 |
-| ⚛️ 对称与不变性 | 群论、几何 | 群作用、不变量、商空间 |
-| 📈 归纳与类比 | 初等数学、数论 | 归纳证明、类比推理、模式识别 |
-| 🖥️ 算法与计算思想 | 计算理论、离散数学 | 复杂度、可计算性、算法范式 |
-| 📡 信息论思想 | 信息论、统计学习 | 熵、互信息、编码极限 |
-| 🎯 博弈论思想 | 数理经济学、机制设计 | 纳什均衡、激励相容、最优策略 |
-| 🔗 因果推断思想 | 因果推断、统计学 | DAG、do-演算、干预分析 |
-| 🌀 拓扑思想 | 拓扑学、代数拓扑 | 同伦、同调、拓扑不变量 |
-| 🧮 离散与组合思想 | 组合数学、图论 | 鸽巢原理、生成函数、枚举 |
-
-## 七、如何选择思想武器
-
-面对一个问题时，最重要的第一步不是”用力分析”，而是”选对工具”。以下是选择指南：
-
-### 快速选择指南
-
-| 问题核心特征 | 最可能适合的思想武器 |
-|-------------|-------------------|
-| 多方互动，我的最优取决于他人 | 🎯 博弈论 |
-| 不确定性/随机性 | 🎲 概率与统计 |
-| 在限制下做最优选择 | ⚖️ 优化 |
-| 当前视角下难以处理 | 🔄 变换 |
-| 需要提取本质结构 | 🧩 抽象化 |
-| 需要严格推理验证 | 🧠 逻辑演绎 |
-| 需要从经验中发现规律 | 📈 归纳与类比 |
-| 需要构建模型预测 | 🌉 建模 |
-| 变化中的不变性 | ⚛️ 对称与不变性 |
-| 需要可执行步骤 | 🖥️ 算法与计算 |
-| 有限对象的计数/结构 | 🧮 离散与组合 |
-
-### 使用激活器
-
-如果不确定该用哪个工具，直接使用 `/ask` 命令调用 math-research-activator，它会诊断问题、映射现代数学结构、推荐 1–3 个最合适的思想武器并做 GPU 可行性筛选。工作区出现算法 / kernel / 模型代码时，激活器也会自动介入。
-
-### 路径
-
-v2 已移除「科研 / 生活双路径」，统一为单一研究 / 算法路径：保留完整数学符号与推导，并在用于算法 / 算子设计时强制过 GPU 八维门。
-
-## 八、如何使用本概述
-
-- 先从问题特征出发：判断它是”结构性””动态性””随机性””交互性”还是”可数性”。
-- 对照快速选择指南或使用 `/ask` 命令，找到最贴近的思想武器。
-- 结合”知识体系层次结构”，判断当前问题更适合基础思路还是前沿方法。
-- 若问题横跨多个类别，可同时调用多个思想武器，例如"建模+优化"、"概率+因果"、"抽象+算法"。
-- 算法 / 算子设计问题可让激活器把现代数学结构（代数几何 / 李理论 / 拓扑等）迁移进来，并过 GPU 八维门。
-- 在学习或阅读文献时，把本概述作为归纳框架，将零散概念归入统一的知识地图。
+深入查阅时，`../../references/books/*.md` 提供 7 本书的蒸馏稿。

package/knowledge-base/probability/concentration-inequality.en.md

@@ -0,0 +1,45 @@
+# Concentration Inequality
+
+## Minimal Definition
+Concentration inequalities bound the **probability that a sum of independent random variables (or a Lipschitz function) deviates from its expectation**. The core intuition: when many independent random factors are superimposed, the outcome is highly concentrated around the mean, with tail probabilities decaying exponentially. They serve as a "quantitative strengthening of the law of large numbers."
+
+## Core Formulas
+
+**Markov's Inequality** (weakest, most general):
+$$P(X \geq a) \leq \frac{\mathbb{E}[X]}{a}, \quad X \geq 0$$
+
+**Hoeffding's Inequality** (sum of bounded independent variables):
+$$P\left(\left|\frac{1}{n}\sum_{i=1}^n X_i - \mathbb{E}\left[\frac{1}{n}\sum X_i\right]\right| \geq t\right) \leq 2\exp\left(-\frac{2n^2 t^2}{\sum(b_i - a_i)^2}\right)$$
+
+**Bernstein's Inequality** (exploits variance information, tighter tails):
+$$P\left(\sum X_i \geq t\right) \leq \exp\left(-\frac{t^2/2}{\sigma^2 + Mt/3}\right)$$
+
+**McDiarmid's Inequality** (bounded-difference functions): If $f$ has sensitivity $c_i$ to changes in the $i$-th variable, then
+$$P(|f(X_1,\ldots,X_n) - \mathbb{E}[f]| \geq t) \leq 2\exp\left(-\frac{2t^2}{\sum c_i^2}\right)$$
+
+## Applicable Problems
+- **Generalization bound derivation**: Given training set size $n$, with what probability does the gap between model predictions and true risk fall within $\epsilon$
+- **Stochastic algorithm reliability**: Probabilistic control of the deviation between mini-batch gradients and full-batch gradients
+- **Sampling estimation accuracy**: Quantitative computation of confidence intervals for Monte Carlo estimators
+
+## AI Design Translation
+- **PAC learning bounds / generalization bounds**: Hoeffding/McDiarmid provides probabilistic bounds on the gap between empirical risk and true risk
+- **Variance control for Dropout / Stochastic Depth**: Bernstein's inequality guarantees output concentration under stochastic regularization
+- **Gradient compression / communication efficiency**: Concentration bounds on gradient deviation after quantization or sparsification, ensuring convergence of distributed training
+
+## Engineering Feasibility
+- **Dimension 1 Tensorization ✅**: The bounds themselves are scalar formulas with no tensor operations; zero overhead as an analytical tool
+- **Dimension 2 GEMM-mappability ✅**: Does not directly participate in GEMM, but can serve as a theoretical basis for hyperparameter selection (batch size, compression ratio)
+- **Dimension 3 Complexity ✅**: Computing the bound itself is $O(1)$ or $O(n)$, very low cost
+- **Dimension 5 Low Precision ✅**: Bounds can be computed in fp32; does not enter the training backbone
+- **Dimension 8 Operator Fusion ✅**: Does not enter the computation graph; no fusion overhead
+
+## Risks and Failure Conditions
+- **Independence assumption violated**: In sequential data and autoregressive models, tokens are strongly correlated, and Hoeffding's exponential decay guarantee fails. Martingale versions (Azuma-Hoeffding) or mixing-time corrections are required.
+- **Boundedness assumption violated**: Under heavy-tailed distributions (e.g., power laws), Hoeffding does not apply; Bernstein or truncation tricks are needed. In LLM training, when gradients occasionally take extreme values, naive concentration bounds yield a false sense of security.
+
+## Further References
+- Distillation draft: `references/books/` — no dedicated probability distillation draft at present; this card is based on standard probability theory textbooks
+- Boucheron, Lugosi, Massart. *Concentration Inequalities: A Nonasymptotic Theory of Independence*. Oxford, 2013
+- Vershynin. *High-Dimensional Probability*. Cambridge, 2018 (Chapters 2-3)
+- Related knowledge cards: `probability/entropy.md`, `probability/fisher-information.md`

package/knowledge-base/probability/concentration-inequality.md

@@ -0,0 +1,45 @@
+# 浓度不等式 / Concentration Inequality
+
+## 最小定义
+浓度不等式界定了**独立随机变量之和（或 Lipschitz 函数）偏离其期望的概率上界**。核心直觉：大量独立随机因素叠加后，结果高度集中在期望附近，尾部概率指数衰减。它是"大数定律的定量加强版"。
+
+## 核心公式
+
+**Markov 不等式**（最弱、最通用）：
+$$P(X \geq a) \leq \frac{\mathbb{E}[X]}{a}, \quad X \geq 0$$
+
+**Hoeffding 不等式**（有界独立变量之和）：
+$$P\left(\left|\frac{1}{n}\sum_{i=1}^n X_i - \mathbb{E}\left[\frac{1}{n}\sum X_i\right]\right| \geq t\right) \leq 2\exp\left(-\frac{2n^2 t^2}{\sum(b_i - a_i)^2}\right)$$
+
+**Bernstein 不等式**（利用方差信息，尾部更紧）：
+$$P\left(\sum X_i \geq t\right) \leq \exp\left(-\frac{t^2/2}{\sigma^2 + Mt/3}\right)$$
+
+**McDiarmid 不等式**（有界差分函数）：若 $f$ 对第 $i$ 个变量的变化敏感度为 $c_i$，则
+$$P(|f(X_1,\ldots,X_n) - \mathbb{E}[f]| \geq t) \leq 2\exp\left(-\frac{2t^2}{\sum c_i^2}\right)$$
+
+## 适用问题
+- **泛化界推导**：给定训练集大小 $n$，模型预测与真实风险之差以多大概率落在 $\epsilon$ 内
+- **随机算法可靠性**：Mini-batch 梯度与全量梯度的偏差概率控制
+- **采样估算精度**：Monte Carlo 估计的置信区间定量计算
+
+## AI 设计翻译
+- **PAC 学习界 / 泛化界**：Hoeffding/McDiarmid → 经验风险与真实风险之差的概率界
+- **Dropout / Stochastic Depth 的方差控制**：Bernstein 不等式给出随机正则化后输出集中度的保证
+- **梯度压缩 / 通信效率**：量化或稀疏化后梯度偏差的浓度界，确保分布式训练收敛
+
+## 工程可行性
+- **维度 1 张量化 ✅**：界本身是标量公式，不涉及张量运算，作为分析工具零开销
+- **维度 2 GEMM 可映射 ✅**：不直接参与 GEMM，但可作为超参数选择（batch size、压缩率）的理论依据
+- **维度 3 复杂度 ✅**：计算界本身 $O(1)$ 或 $O(n)$，极低
+- **维度 5 低精度 ✅**：界用 fp32 计算即可，不进入训练主干
+- **维度 8 算子融合 ✅**：不进入计算图，无融合负担
+
+## 风险与失效条件
+- **独立性假设不成立**：序列数据、自回归模型中 token 间强相关，Hoeffding 的指数衰减保证失效。需用 Martingale 版本（Azuma-Hoeffding）或混合时间修正。
+- **有界性假设违反**：重尾分布（如幂律）下 Hoeffding 不适用，需改用 Bernstein 或截断技巧。在 LLM 训练中梯度偶尔出现极大值时，朴素浓度界给出虚假安全感。
+
+## 深入参考
+- 蒸馏稿：`references/books/` 暂无专用概率蒸馏稿，本卡基于标准概率论教材
+- Boucheron, Lugosi, Massart. *Concentration Inequalities: A Nonasymptotic Theory of Independence*. Oxford, 2013
+- Vershynin. *High-Dimensional Probability*. Cambridge, 2018（第 2-3 章）
+- 关联知识卡：`probability/entropy.md`、`probability/fisher-information.md`