Information Geometry
@SN_INGE
Followers
2K
Following
1K
Media
187
Statuses
2K
Journal: Geometric methods for #Computerscience #Statistics #ML #QuantumPhysics #OptimalTransport #AI #DifferentialGeometry Submit: https://t.co/dD8qAQVbZa 🚀
Mathematics, SpringerNature
Joined October 2021
🏆Good News. The journal Information Geometry has received its first #ImpactFactor of 🌟1.2🌟! Ranked as Q1 (84th/483) in SCIE/ESCI mathematics journals worldwide.👏👏👏 👉 https://t.co/Ej4fnKJCuB cf. CiteScore @Scopus 2024: 2.0 Thanks to all our authors, reviewers and editors!
0
13
37
Shun-ichi Amari (Professor Emeritus, The University of Tokyo; Founder of Information Geometry) “The Birth and Development of Information Geometry” https://t.co/eaecr2nSY3
mathexpo2025.peatix.com
開催予定 : 2025年12月20(土曜日)10:00~16:30(受付 9:40~予定)会 場 : TKP高輪ゲートウェイカンファレンスセンター 「ホール 2B」 出演者(敬称... powered by Peatix : More than a ticket.
🎓出演者紹介|甘利俊一教授 数理工学と神経科学を融合し「情報幾何学」を創始。AIや脳研究の理論基盤を築いた日本を代表する数理科学者。 🎟️チケット👇 https://t.co/VRdiQb2spa #甘利俊一 #情報幾何学 #数学 #AI #脳科学
0
2
3
✨ Just appeared in #informationgeometry Mohammad Emtiyaz Khan @RIKEN_AIP_EN: "Information Geometry of Variational Bayes " #NaturalGradientDescent
#HalfACenturyOfInformationGeometry Part 2 Free view 🔗 https://t.co/WKFRJQ7nvu
https://t.co/kidVVkawSi
link.springer.com
Information Geometry - We highlight a fundamental connection between information geometry and variational Bayes (VB) and discuss its consequences for machine learning. Under certain conditions, a...
0
6
22
✨ Just appeared in #informationgeometry Shinto Eguchi, Shogo Kato @tousuuken: "Minimum copula divergence for robust estimation" #Misspecification #江口真透 #加藤昇吾 Free view 🔗 https://t.co/w7RLUgqzh2
https://t.co/iAMQ6lkkmX
link.springer.com
Information Geometry - This paper introduces a robust estimation framework based solely on the copula function. We begin by introducing a family of divergence measures tailored for copulas,...
1
6
19
Information geometry of Chernoff information (aka exponent error in Bayesian hypothesis testing): Meet the Chernoff point! Closed-form formula for univariate Gaussians with symbolic computing, fast approximation algorithm for multivariate Gaussians
4
35
241
✨ Just appeared in #informationgeometry Roozbeh Yousefzadeh @Yale: "Deep learning generalization and the convex hull of training sets" #InformationGeometryforDeepLearning Free view 🔗 https://t.co/SOf7xHwz62
https://t.co/5NlGa7KEJT
link.springer.com
Information Geometry - We study the generalization of deep learning models in relation to the convex hull of their training sets. Through an empirical analysis of machine learning benchmarks for...
1
0
8
✨ Just appeared in #informationgeometry Shotaro Akaho @AIST_JP, Hideaki Ishibashi @kyutech: "Information geometry of Gaussian processes and its applications to transfer learning" #FDIG2025 #赤穗昭太郎 #石橋英朗 🔓 #OpenAccess
https://t.co/nW0uhrc8ZJ
link.springer.com
Information Geometry - Gaussian Processes (GPs) are widely used in machine learning for modeling complex functions with uncertainty quantification. Yet their infinite-dimensional nature creates...
0
12
22
✨ Just appeared in #informationgeometry Yo Sheena @shiga_ds_info: "Efficiency of maximum likelihood estimation for a multinomial distribution with known probability sums" #KullbackLeiblerdivergence #椎名洋 🔓 #OpenAccess
https://t.co/9wJsH6TfYk
link.springer.com
Information Geometry - For a multinomial distribution, suppose we have prior knowledge about the sum of the probabilities of certain categories. This enables the construction of a submodel within...
0
4
9
Keynote talk at GSI'25 on non-parametric information geometry: The Lp Fisher-Rao metrics and the alpha-connections by Alice Le Brigant (Université Paris 1 Panthéon-Sorbonne, France) Paper published in @SN_INGE in open access: https://t.co/VpMfRV8ejp
https://t.co/xwnhGu8yE1
1
6
19
Next week!!! 7th International Conference on "Geometric Science of Information" (GSI) Web site: https://t.co/Pd97YcDfME
0
7
29
🎖️The 2025 #ShawPrize Mathematical Sciences will be presented to Kenji Fukaya on 21 October in Hong Kong! 🔓To celebrate, we’ve opened access to his articles and selected book chapters published with #SpringerNature here: https://t.co/psckVsWkbS 🎉🎉🎉 #FreeDownload til Nov 20
0
15
32
✨ Just appeared in #informationgeometry Yutaro Kabata, Hirotaka Matsumoto, Seiichi Uchida, Masao Ueki: @NU_kouhou, @KyushuUniv_EN "Singularities in bivariate normal mixtures" https://t.co/Xw3pZNdnag 🔓 #OpenAccess
link.springer.com
Information Geometry - We investigate mappings whose components are bivariate normal densities from the perspective of singularity theory. Motivated by the need to understand two-component...
0
5
11
✨ Just appeared in #informationgeometry Keita Nakamura, Tomoyuki Nakagawa, Kouji Tahata: "Quasi-symmetry and geometric marginal homogeneity: a simplicial approach to square contingency tables" https://t.co/e5QFlCh3Mx
#FDIG2025 @TUS_PR_en, @RIKEN_CBS 🔓 #OpenAccess
1
5
6
✨ Just appeared in #informationgeometry Hayato Nishimori, Takeru Matsuda #UTokyo @RIKEN_CBS: "On the attainment of the Wasserstein–Cramer–Rao lower bound" https://t.co/0b0wv7zLfG
#FDIG2025 🔓 #OpenAccess
0
2
7
2025 update (easy to find on the web): A Nobel Prize for Plagiarism. Technical Report IDSIA-24-24, 2024, updated Oct 2025 (26 pages, 5 illustrations, 200+ references). Abstract: Sadly, the 2024 Nobel Prize in Physics awarded to Hopfield & Hinton is effectively a prize for
3
8
59
The 2025 Kyoto Prize Kyoto Prize Laureate Prof. Shun-ichi Amari / Mathematical Engineer Lecture topics: "My Life Has Been Lucky!" 2025 11/11 Tue 13:00 - 16:10 https://t.co/zZZ56sVTb6
0
8
41
✨ Just appeared in #informationgeometry Jun-ichi Inoguchi, Yu Ohno @HokkaidoUni: "Homogeneous statistical manifolds" Dedicated to Professor Takashi Kurose on the occasion of his 60th birthday. #Liegroup Free view 🔗 https://t.co/SdLB7U6IeV
https://t.co/wjOyxdWhLr
1
3
16
✨ Just appeared in #informationgeometry Tatsuo Suzuki @shibaura_it: "An explicit formula for Hessian potentials on warped product manifolds" https://t.co/SwyPL0AOec
#FDIG2025 #Hessianmanifold #Affinedifferentialgeometry 🔓 #OpenAccess
0
3
6