Overview

Information geometry treats probability distributions as points on a statistical manifold, with the Fisher information metric measuring distinguishability and KL or Bregman divergences describing separation. Its core tools include natural gradients, exponential-family duality, curvature analysis, and pullback metrics that account for how models map parameters or representations to distributions. These methods are used in settings such as deep-network optimization and steering, generative-model sampling, Bayesian inference, and robustness under distribution shift. A central challenge is that Fisher geometry can be expensive or noisy to estimate, and the value of its invariant, task-sensitive metrics depends on which approximation and model setting are used.

Latest papers

CardsList

68 papers9 papers in the last four weeks, up 50% on the four weeks before. 0.1% of all new papers.

  1. Hermitian Positive Definite Neural Networks for Matrix-CFAR Geometric Signal Detection in Nonhomogeneous Clutter

    Nov 15, 2026Xiyao Chen, Takumi Sato, Linyu PengInformation Geometry

  2. Bregman geometry in regular exponential families: dual representations and relative smoothness

    Nov 13, 2026Mame Diarra Fall, Éric Barat, Nicolas DobigeonExponential FamilyInformation Geometry

  3. Confronting Uncertainty in Mechanism-AI Coupled Dynamical Systems via Optimal Transport and Information Geometry: Part I. Distribution Learning

    Nov 7, 2026Pengfei Song, Yanni Xiao, Shuangshuang YinUncertainty QuantificationDynamical Systems

  4. Bridging Singular Learning Theory and Mechanistic Interpretability at the Billion-Parameter Scale

    Oct 31, 2026Ethan Ji, Wei Wang, Yizhou SunMechanistic InterpretabilitySingular Learning Theory

  5. The Geometry of Manifold Learning: Singular foliations via Deep Learning models

    Oct 27, 2026Gabriele Novelli, Eliot Tron, Emanuele Latini +1Neural Representation GeometryManifold Learning

  6. Intrinsic Information-Theoretic Analysis of ReLU Nets

    Oct 27, 2026Johan Mylius-Kroken, Elisabeth Wetzer, Ali Ramezani-Kebrya +2ReLU Neural NetworksMutual Information Estimation

  7. The Information Geometry of Representation Formation

    Oct 25, 2026Sanjukta KrishnagopalNeural Representation GeometryInformation Geometry

  8. The Bayesian Learning Rule Beyond KL Geometry

    Oct 22, 2026Sophia Sklaviadis, Wu Lin, Andre Martins +3Bayesian InferenceVariational Inference

  9. Information-Geometric Blind Spots of Conformal Test Martingales

    Oct 16, 2026Johan Hallberg SzabadváryDistribution Shift DetectionConformal Prediction

  10. How Inefficient Is Natural Gradient Descent? From Exact Optimality to Θ( \sqrt{ \log d } ) Divergence

    Oct 5, 2026Guni Sharon, Alan KuhnleInformation GeometryRiemannian Optimization

  11. Technical note on: Zero-Training Feature-Space Alignment via Information Geometry

    Sep 29, 2026Behraj Khan, Tahir Qasim Syed, Syed Ahmad Chan BukhariDistribution Shift RobustnessInformation Geometry

  12. Fisher-IRG: Fisher-Induced Local Invariant Representation Geometry across Language and Vision Models

    Sep 29, 2026Abdullah All Tanvir, Xin ZhongInformation GeometryNeural Representation Geometry

  13. Reducing the Adaptation Gap Through Reachable Fisher Geometry

    Sep 28, 2026Wasif Jalal, Sachin Deb, Asif SalekinParameter-Efficient Fine-TuningGroup Fairness

  14. Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods

    Sep 25, 2026Saksham Kiroriwal, Julius Pfrommer, Jürgen BeyererBayesian OptimizationTrust-Region Optimization

  15. Information Geometric Self-Organization at the Edge of Stability in High-Capacity Kernel Associative Memories

    Sep 15, 2026Akira TamamoriInformation GeometryEdge of Stability

  16. Geometry of learning dynamics: Gradient descent versus natural gradient on the ridge of optimization

    Sep 15, 2026Akira TamamoriInformation GeometryGradient Descent

  17. The information geometry of large language models is shared, learned, and controllable

    Sep 10, 2026Dario PicozziInformation GeometryLanguage Model Steering

  18. A Generalization of Amari's Bayesian Duality

    Sep 8, 2026Mohammad Emtiyaz Khan, Thomas MöllenhoffInformation GeometryBayesian Inference

  19. The Dually Flat Geometry of Planning as Inference

    Sep 3, 2026Nikola Milosevic, Asaki Kataoka, Nicolas Hinrichs +2Information GeometryNatural Policy Gradient

  20. Informative Label Missingness in Multiclass Classification Information Geometry and Excess Risk

    Aug 31, 2026Fariborz Setoudehtazang, Geoffrey J. McLachlanInformation GeometryLearning with Missing Data

  21. The information geometry of product-reference discrete diffusion: Interaction growth complexity and optimal scheduling

    Aug 28, 2026Martin J. WainwrightDiscrete Diffusion SamplingDiffusion Sampling

  22. The Loss Floor of Denoising Score Matching: Fisher Geometry from Schrödinger Bridges

    Aug 24, 2026Avinash Raju, Kai ZhangScore-Based Generative ModelingDiffusion Models

  23. Loss-Parameterized Fisher Width Along Learning Trajectories

    Aug 21, 2026Vu Khac KyFisher InformationNeural Network Training Dynamics

  24. Information Geometry of Message Passing

    Aug 16, 2026Mykola Lukashchuk, Kyrylo Yemets, Alex Ledbetter +1Belief PropagationProbabilistic Graphical Models

  25. The Advective Fisher-Rao Geometry of Deterministic Measure Transport

    Aug 12, 2026Benjamin Gess, Johannes MüllerInformation GeometryRiemannian Optimization

  26. Information-Geometric Forward Policy Training in GFlowNets

    Aug 4, 2026Yordan Raykov, Rodrigo VeigaInformation GeometryNatural Gradient Methods