mlsanityData to 14 Oct 2026

Information-Geometric Optimization on Spheres

arXiv 2606.07588 ↗First posted 27 May 2026cs.NE cs.LG math.OCcited by 0

Not on the map. Why?

Abstract (arXiv)

We consider the black-box optimization problem on a sphere. Two information-geometric optimization flows (IGO flows) are designed with rigorous calculation of natural search gradients based on hyperbolic (information) geometry of Poincar' e and Bergman balls. We demonstrate that ensembles of generalized Kuramoto oscillators on spheres compute natural search gradients and realize IGO algorithms on both manifolds. The relationship between natural gradient policies in Bergman balls and quantum decision making is pointed out.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 9 of its 45 references that are in the map. First posted on arXiv 27 May 2026.

Builds on

9 of 45 references.

References · 9

  1. 2015Trust Region Policy Optimizationcited by 2,580
  2. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 574
  3. 2019Quantum Natural Gradientcited by 106
  4. 2019Spherical Text Embeddingcited by 49
  5. 2022Hyperbolic Deep Reinforcement Learningcited by 25
  6. 2020Natural Evolutionary Strategies for Variational Quantum Computationcited by 15
  7. 2022Bingham Policy Parameterization for 3D Rotations in Reinforcement Learningcited by 8
  8. 2025A group-theoretic framework for machine learning in hyperbolic spacescited by 3
  9. 2018Mean field repulsive Kuramoto models: Phase locking and spatial signscited by 2

Built on by

Not cited yet.