{"product_id":"mathematical-foundations-of-trustworthy-ai-theory-algorithms-and-engineering-principles-paperback","title":"Mathematical Foundations of Trustworthy AI: Theory, Algorithms, and Engineering Principles - Paperback","description":"\u003cdiv\u003e\u003cp style=\"text-align: right;\"\u003e\u003ca href=\"https:\/\/reportcopyrightinfringement.com\/\" target=\"_blank\" rel=\"nofollow\"\u003e\u003cb\u003eReport copyright infringement\u003c\/b\u003e\u003c\/a\u003e\u003c\/p\u003e\u003c\/div\u003e\u003cp\u003eby \u003cb\u003eAizierjiang Aiersilan\u003c\/b\u003e (Author)\u003c\/p\u003e\u003cp\u003e\u003c\/p\u003e\u003cp\u003e\u003cstrong\u003eMathematical Foundations of Trustworthy AI: Theory, Algorithms, and Engineering Principles\u003c\/strong\u003e offers a systematic, textbook-style treatment of the mathematics behind safe, fair, private, and reliable machine learning. It brings together, under a single cover, the core theoretical results from constrained optimization, statistical learning theory, and differential geometry that underpin robustness, fairness, privacy, explainability, causality, and safety in modern AI systems.\u003c\/p\u003e\u003cp\u003eThe book is organized into five parts and a comprehensive appendix: \u003c\/p\u003e\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePart I - Foundations \u0026amp; Theory: \u003c\/strong\u003e notation, the necessity of trust, and statistical learning theory (concentration inequalities, VC dimension, Rademacher complexity, PAC learning, algorithmic stability, double descent).\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003ePart II - Robustness, Fairness, Privacy: \u003c\/strong\u003e adversarial attacks (FGSM, PGD, C\u0026amp;W, AutoAttack) and certified defenses via randomized smoothing; group, individual, and causal fairness with impossibility theorems (Kleinberg-Chouldechova); differential privacy with composition, Rényi DP, and DP-SGD accounting.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003ePart III - Interpretability \u0026amp; Causality: \u003c\/strong\u003e Shapley values, LIME, integrated gradients, concept-based XAI; structural causal models, the do-calculus, counterfactuals, front-door adjustment, and algorithmic recourse.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003ePart IV - Distributed Learning \u0026amp; Decision Making: \u003c\/strong\u003e federated learning (FedAvg, FedProx, Byzantine robustness); safe reinforcement learning (CMDPs, control barrier functions, RLHF, DPO); out-of-distribution detection and conformal prediction.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003ePart V - Engineering, Governance, Frontiers: \u003c\/strong\u003e formal verification of neural networks, MLOps for trustworthy AI, AI governance; Lipschitz and monotonic networks, robust statistics, shuffle-model privacy; trustworthy agentic AI and open research directions.\u003c\/li\u003e\n\u003c\/ul\u003e\u003cp\u003eAppendices supply mathematical prerequisites, extended proofs, reference Python implementations, evaluation metrics, and a glossary of key terms.\u003c\/p\u003e\u003cp\u003eThroughout, trust is treated as a quantifiable property rather than a slogan: every informal desideratum is reduced to mathematical objects with explicit guarantees, sample complexities, or impossibility results. Each theorem is paired with a worked example, a Python implementation, or an evaluation protocol, so the chain from theory to deployable algorithm is never left implicit. Each chapter includes worked problems and exercises.\u003c\/p\u003e\u003cp\u003eIntended for graduate students, researchers, and practitioners who seek precise mathematical statements, rigorous proofs, and concrete examples in the rapidly evolving field of Trustworthy AI.\u003c\/p\u003e\n            \u003cdiv\u003e\n\u003cstrong\u003eNumber of Pages:\u003c\/strong\u003e 338\u003c\/div\u003e\n            \u003cdiv\u003e\n\u003cstrong\u003eDimensions:\u003c\/strong\u003e 0.7 x 10 x 7 IN\u003c\/div\u003e\n            \u003cdiv\u003e\n\u003cstrong\u003ePublication Date:\u003c\/strong\u003e August 31, 2026\u003c\/div\u003e\n            ","brand":"BooksCloud","offers":[{"title":"Default Title","offer_id":54089520841011,"sku":"9798996081806","price":50.18,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0300\/5595\/6612\/files\/qCqI4H4qJu9798996081806.webp?v=1789592019","url":"https:\/\/www.vysn.com\/products\/mathematical-foundations-of-trustworthy-ai-theory-algorithms-and-engineering-principles-paperback","provider":"VYSN","version":"1.0","type":"link"}