On the robustness of noisy solutions in non-convex neural networks

arXiv:2607.27000 · cond-mat.dis-nn, cs.LG, math.PR · Submitted 2026-07-29 · Read on arXiv

cond-mat.dis-nn, cs.LG, math.PR

Submitted: 2026-07-29

Updated: 2026-09-25

Terminology

• Generalization — 35× in this paper · explained in 13 episodes
• Loss Function — 5× in this paper · explained in 2 episodes
• Approximate Message Passing — 4× in this paper
• Robustness — 3× in this paper · explained in 5 episodes
• alpha — 3× in this paper · explained in 1 episode
• Hamming Distance — 2× in this paper · explained in 2 episodes
• Symmetry Breaking — 2× in this paper · explained in 3 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Hypergraph — 1× in this paper · explained in 2 episodes

Sources

• Scaling Laws for Neural Language Models
• Parametric RDT approach to computational gap of symmetric binary perceptron
• Ultrametric OGP - parametric RDT \emph{symmetric} binary perceptron connection
• Finding the right path: statistical mechanics of connected solutions in constraint satisfaction problems
• High-dimensional manifold of solutions in neural networks: insights from statistical physics

Related papers

• Few-Shot Neuromorphic Vision in a Nonlinear Photonic Network Laser
• Hyperbolic lattices with mass disorder: Phases and phase transitions
• Adaptive Neural Quantum States: A Recurrent Neural Network Perspective
• Machine learning Majorana topology using unsupervised and supervised learning
• Quenched fluctuation-induced force arising from polarization disorder