collaborators

6 papers

q-bio.PE2026

Geometric framework for biological evolution

Vitaly Vanchurin

We develop a generally covariant description of evolutionary dynamics that operates consistently in both genotype and phenotype spaces. We show that the maximum entropy principle y…

cs.LG2026

Geometric Learning Dynamics

Vitaly Vanchurin

We present a unified geometric framework for modeling learning dynamics in physical, biological, and machine learning systems. The theory reveals three fundamental regimes, each em…

hep-th2025

Emergent field theories from neural networks

Vitaly Vanchurin

We establish a duality relation between Hamiltonian systems and neural network-based learning systems. We show that the Hamilton's equations for position and momentum variables cor…

physics.chem-ph2025

Molecular Learning Dynamics

Yaroslav Gusev, Vitaly Vanchurin

We apply the physics-learning duality to molecular systems by complementing the physical description of interacting particles with a dual learning description, where each particle…

cs.LG2025

Covariant Gradient Descent

Dmitry Guskov, Vitaly Vanchurin

We present a manifestly covariant formulation of the gradient descent method, ensuring consistency across arbitrary coordinate systems and general curved trainable spaces. The opti…

cs.LG2025

Dataset-learning duality and emergent criticality

Ekaterina Kukleva, Vitaly Vanchurin

In artificial neural networks, the activation dynamics of non-trainable variables is strongly coupled to the learning dynamics of trainable variables. During the activation pass, t…