The transition between synchronization and chaos for random Blaschke products
arXiv:2607.15488
2026
Dynamics
2 ideas extracted · analyzed Aug 30, 2026
What the math gives to ML
The paper provides a mechanism for an order-to-chaos transition in random compositions of disk-preserving Blaschke maps. Its transferable asset is a computable random-dynamical-systems certificate: average logarithmic derivative growth distinguishes synchronization from desynchronization, while the disk geometry prevents radial explosion. A neural implementation can use complex-valued recurrent states constrained to the unit disk, with randomly switched Blaschke transitions and an online estimate of the transverse Lyapunov exponent. The resulting architecture exposes a measurable transition boundary that can be tested independently of downstream benchmark performance.
Ideas from this paper
△ Mechanism confirmed, baseline not beaten
2026
Replace an unconstrained recurrent transition by a randomly switched composition of disk-preserving Blaschke maps. The recurrent state remains in the unit disk, while the estimated average logarithmic derivative provides a direct synchronization-versus-chaos control knob: negative transverse growth should make two states driven by the same input or map sequence synchronize, whereas positive growth should preserve sensitivity and expressive memory.
Useful8/10
Difficulty6/10
Novelty7/10
✗ Failed on benchmark
2026
Use the paper's random fixed-point attractor and associated Poisson-kernel invariant density as an explicit distributional target for an ensemble of recurrent latent states. Instead of forcing hidden states toward zero, estimate the attractor induced by the recent random map sequence and regularize the ensemble toward its analytically specified angular density.
Useful7/10
Difficulty5/10
Novelty8/10