Information geometry

수학노트
Pythagoras0 (토론 | 기여)님의 2021년 2월 21일 (일) 20:56 판 (→‎노트: 새 문단)
(차이) ← 이전 판 | 최신판 (차이) | 다음 판 → (차이)
둘러보기로 가기 검색하러 가기

노트

말뭉치

  1. One useful aspect of information geometry is that it gives a means to prove results about statistical models, simply by considering them as well-behaved geometrical objects.[1]
  2. Coverage includes original work and synthesis exploring the foundation and application of information geometry in both mathematical and computational aspects.[2]
  3. To this extent, I recently stumbled across information geometry.[3]
  4. Remarkably however, as we shall see, the statistical manifolds of information geometry turn out to have a uniquely appropriate metric.[4]
  5. We have now covered enough basic concepts of differential geometry to begin to discuss information geometry.[4]
  6. Abstract We begin a global study of information geometry.[5]
  7. We illustrate the result by working out the details of the information geometry of a physically relevant two-level system.[6]
  8. In brief, any (weakly mixing) random dynamical system that possesses a Markov blanket—i.e. a separation of internal and external states—is equipped with an information geometry.[7]
  9. The conditional dependencies this implies equip the internal states of the system with an information geometry for a space of (Bayesian) beliefs about the external states.[7]
  10. Consequently, the internal state-space has an inherent information geometry (technically, this space is a statistical manifold).[7]
  11. Equation (2.3) implies an information geometry that links the statistics of the two, in virtue of the boundary that separates them.[7]
  12. We propose a unified framework for quantifying any combination of causal relationships between elements in a hierarchical manner based on information geometry.[8]
  13. To resolve these difficulties, we propose a theoretical framework based on information geometry for the quantification of multiple causal influences with a holistic approach.[8]
  14. To overcome these problems, we propose a unified framework for quantifying causal influences based on information geometry (22).[8]
  15. In this paper, we proposed a unified framework based on information geometry, which enables us to quantify multiple influences without overestimation and confounds of noncausal influences.[8]
  16. The semi-Riemannian metric of this hypothesis space is uniquely derived in closed form based on the information geometry of probability distributions.[9]
  17. One very nice thing about information geometry is that it gives us very strong tools for proving results about statistical models, simply by considering them as well-behaved geometrical objects.[10]
  18. Since differential geometry lets me do coordinate-free physics, information geometry seems like an appealing way to do this.[10]
  19. Here, the information geometry is studied for a number of solvable statistical–mechanical models.[11]
  20. It reached maturity through the work of Shun'ichi Amari in the 1980s, with what is currently the canonical reference book: Methods of information geometry.[12]
  21. This journal will publish original work in the emerging interdisciplinary field of information geometry, with both a theoretical and computational emphasis.[13]
  22. Information geometry connects various branches of mathematical science in dealing with uncertainty and information based on unifying geometric concepts.[13]
  23. The purpose of this international conference is to exchange recent developments in information geometry and to establish its theoretical foundations in related fields.[14]
  24. I present a general theory of mean-field approximation based on information geometry and applicable not only to Boltzmann machines but also to wider classes of statistical models.[15]
  25. Abstract: Using ideas from information geometry we seek to develop a quantitative measure of complexity.[16]
  26. The journal will publish papers on such research along with those on application of information geometry, broadly construed, emphasizing both theoretical and computational aspects.[17]
  27. This is the first comprehensive book on information geometry, written by the founder of the field.[18]
  28. A manifold with a divergence function is first introduced, leading directly to dualistic structure, the heart of information geometry.[18]
  29. Information geometry of statistical inference, including time series analysis and semiparametric estimation (the Neyman–Scott problem), is demonstrated concisely in Part III.[18]
  30. Information geometry has emerged from studies of invariant geometrical structure involved in statistical inference.[19]

소스