Dynamical mean field theory for models of confluent tissues and beyond

Abstract

We consider a recently proposed model to understand the rigidity transition in confluent tissues and we derive the dynamical mean field theory (DMFT) equations that describes several types of dynamics of the model in the thermodynamic limit: gradient descent, thermal Langevin noise and active drive. In particular we focus on gradient descent dynamics and we integrate numerically the corresponding DMFT equations. In this case we show that gradient descent is blind to the zero temperature replica symmetry breaking (RSB) transition point. This means that, even if the Gibbs measure in the zero temperature limit displays RSB, this algorithm is able to find its way to a zero energy configuration. We include a discussion on possible extensions of the DMFT derivation to study problems rooted in high-dimensional regression and optimization via the square loss function.

arXiv comment20 pages, 6 figures, Submission to SciPost

References in corpus (24)

• A high-bias, low-variance introduction to Machine Learning for physicists
• A density-independent glass transition in biological tissues
• Motility-driven glass and jamming transitions in biological tissues
• Fractal free energy landscapes in structural glasses
• Spin-Glass Theory for Pedestrians
• Energy barriers govern glassy dynamics in tissues
• A geometrically controlled rigidity transition in a model for confluent 3D tissues
• The simplest model of jamming
• Universality of the SAT-UNSAT (jamming) threshold in non-convex continuous constraint satisfaction problems
• Multicellular rosettes drive fluid-solid transition in epithelial tissues
• Shear yielding and shear jamming of dense hard sphere glasses
• Locked constraint satisfaction problems
• Rethinking mean-field glassy dynamics and its relation with the energy landscape: the awkward case of the spherical mixed p-spin model
• Out-of-equilibrium dynamical mean-field equations for the perceptron model
• Jamming in multilayer supervised learning models
• Critical jammed phase of the linear perceptron
• Out-of-equilibrium dynamical equations of infinite-dimensional particle systems. I. The isotropic case
• A spin glass model for reconstructing nonlinearly encrypted signals corrupted by noise
• A continuous constraint satisfaction problem for the rigidity transition in confluent tissues
• High dimensional optimization under non-convex excluded volume constraints
• Surfing on minima of isostatic landscapes: avalanches and unjamming transition
• Quantum exploration of high-dimensional canyon landscapes
• Recent Applications of Dynamical Mean-Field Methods
• Six Lectures on Linearized Neural Networks

Cited by in corpus (3)

• On the topology of solutions to random continuous constraint satisfaction problems
• Stochastic Gradient Descent outperforms Gradient Descent in recovering a high-dimensional signal in a glassy energy landscape
• Bilinear Sequence Regression: A Model for Learning from Long Sequences of High-dimensional Tokens