Statistical Learning 스터디

스터디 주제

• Category Theory

  • Category 이론의 주요 개념
  • 현대 수학의 주요 개념에 대한 이해
  • 구조주의와 머신 러닝 기법

• Statistical Mahcine Learning

  • Probabilistic Data Generation
  • (A)PAC Learnability & VC Dimension
  • 각종 머신러닝 기법의 이론적 이해

• Various Paper Reviews

스터디 키워드

Prior Knowledge, Degree of Freedom, Structuralism, Applied Mathematics, Language Model, Reasoning.

스터디 일정

• 2026-05-30 (Done)
  • 왜 Category Theory를 공부해야 하는가
  • Algebraic Structures and Preorder
• 2026-06-06 (Done)
  • Category, Functor, Natural Transformation (1)
• 2026-06-29 (Done)
  • Natural Transformation (2), Limit, Adjoints
• 2026-07-04 (Done)
  • PAC Learnability, APAC Learnability, VC Dimension
• 2026-07-11 (Done)
  • Presheaf and Sheaf, Lawvere’s Fixed Point Theorem, Linear Model, Boosting
• 2026-07-21 Offline (Done)
  • Review of the Previous Studies
• 2026-08-01
  • Model Selection and Validation, Regularization and Stability
  • Paper Review: Antropic, Verbalizable Representations Form a Global Workspace in Language Models. (Link)
• 2026-08-08
  • Paper Review: Jared Kaplan et al. Scaling Laws for Neural Language Models.

참고문헌

(Category Theory)
Mac Lane, Categories for the Working Mathematicians
Brendan Fong, David I. Spivak, Seven Sketches in Compositionality

(Statistical Machine Learning)
Shai Shalev-Shwartz, Shai Ben-David, Understanding Machine Learning
Trevor Hastie, Robert Tibshirani, Jerome Friedman, The Elements of Statistical Learning
George Casella, Roger L. Berger, Statistical Inference

(Information Theory)
Joy A. Thomas and Thomas M. Cover, Elements of Information Theory

(Paper Review)
Antropic, Verbalizable Representations Form a Global Workspace in Language Models. (Link)
Jared Kaplan et al. Scaling Laws for Neural Language Models.

참가 문의