Neural network realization of binary refinement iterates via a two-chart atlas selector

arXiv:2608.02624 · math.NA, cs.LG, stat.ML · Submitted 2026-07-21 · Read on arXiv

Tsogtgerel Gantumur

math.NA, cs.LG, stat.ML

Submitted: 2026-07-21

Comments: 30 pages

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• ReLU Network — 10× in this paper · explained in 2 episodes
• Localization — 4× in this paper · explained in 2 episodes
• Neural Network Approximation — 2× in this paper · explained in 2 episodes
• Absorb — 1× in this paper · explained in 1 episode
• Composition — 1× in this paper · explained in 2 episodes
• Fixed Point — 1× in this paper · explained in 2 episodes

Sources

• Exact Loop Controllers for ReLU Realization of Homogeneous Curve Refinements

Related papers

• Do physics-informed neural networks (PINNs) need to be deep? Shallow PINNs using the Levenberg-Marquardt algorithm
• A Neural-preconditioned Poisson Solver for Mixed Dirichlet and Neumann Boundary Conditions
• Advanced Linear Algebra with Applications - Part I (Numerical linear algebra for PDEs, machine learning, and data assimilation)
• Operator learning meets inverse problems: A probabilistic perspective
• Second-order consistency for learning chaotic dynamics via randomized Jacobian matching
• Windowed thinning and query complexity for the bouncy particle and Zigzag samplers