An optimization-based equilibrium measure describes non-equilibrium steady state dynamics: application to edge of chaos

• URL: http://arxiv.org/abs/2401.10009v2
• Date: Fri, 7 Jun 2024 06:29:08 GMT
• Title: An optimization-based equilibrium measure describes non-equilibrium steady state dynamics: application to edge of chaos
• Authors: Junbin Qiu, Haiping Huang,
• Abstract summary: Understanding neural dynamics is a central topic in machine learning, non-linear physics and neuroscience. The dynamics is non-linear, and particularly non-gradient, i.e., the driving force can not be written as gradient of a potential.
• Score: 2.5690340428649328
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding neural dynamics is a central topic in machine learning, non-linear physics and neuroscience. However, the dynamics is non-linear, stochastic and particularly non-gradient, i.e., the driving force can not be written as gradient of a potential. These features make analytic studies very challenging. The common tool is the path integral approach or dynamical mean-field theory, but the drawback is that one has to solve the integro-differential or dynamical mean-field equations, which is computationally expensive and has no closed form solutions in general. From the aspect of associated Fokker-Planck equation, the steady state solution is generally unknown. Here, we treat searching for the steady states as an optimization problem, and construct an approximate potential related to the speed of the dynamics, and find that searching for the ground state of this potential is equivalent to running an approximate stochastic gradient dynamics or Langevin dynamics. Only in the zero temperature limit, the distribution of the original steady states can be achieved. The resultant stationary state of the dynamics follows exactly the canonical Boltzmann measure. Within this framework, the quenched disorder intrinsic in the neural networks can be averaged out by applying the replica method, which leads naturally to order parameters for the non-equilibrium steady states. Our theory reproduces the well-known result of edge-of-chaos, and further the order parameters characterizing the continuous transition are derived, and the order parameters are explained as fluctuations and responses of the steady states. Our method thus opens the door to analytically study the steady state landscape of the deterministic or stochastic high dimensional dynamics.

Related papers

• Is the effective potential, effective for dynamics? [8.273855626116564]
  Energy conservation leads to the emergence of highly excited, entangled stationary states from the dynamical evolution. The results suggest novel characterization of equilibrium states in terms of order parameter vs. energy density.
  arXiv  Detail & Related papers  (2024-03-11T18:19:06Z)
• Machine learning in and out of equilibrium [58.88325379746631]
  Our study uses a Fokker-Planck approach, adapted from statistical physics, to explore these parallels. We focus in particular on the stationary state of the system in the long-time limit, which in conventional SGD is out of equilibrium. We propose a new variation of Langevin dynamics (SGLD) that harnesses without replacement minibatching.
  arXiv  Detail & Related papers  (2023-06-06T09:12:49Z)
• An information field theory approach to Bayesian state and parameter estimation in dynamical systems [0.0]
  This paper develops a scalable Bayesian approach to state and parameter estimation suitable for continuous-time, deterministic dynamical systems. We construct a physics-informed prior probability measure on the function space of system responses so that functions that satisfy the physics are more likely.
  arXiv  Detail & Related papers  (2023-06-03T16:36:43Z)
• Global Convergence of Over-parameterized Deep Equilibrium Models [52.65330015267245]
  A deep equilibrium model (DEQ) is implicitly defined through an equilibrium point of an infinite-depth weight-tied model with an input-injection. Instead of infinite computations, it solves an equilibrium point directly with root-finding and computes gradients with implicit differentiation. We propose a novel probabilistic framework to overcome the technical difficulty in the non-asymptotic analysis of infinite-depth weight-tied models.
  arXiv  Detail & Related papers  (2022-05-27T08:00:13Z)
• Decimation technique for open quantum systems: a case study with driven-dissipative bosonic chains [62.997667081978825]
  Unavoidable coupling of quantum systems to external degrees of freedom leads to dissipative (non-unitary) dynamics. We introduce a method to deal with these systems based on the calculation of (dissipative) lattice Green's function. We illustrate the power of this method with several examples of driven-dissipative bosonic chains of increasing complexity.
  arXiv  Detail & Related papers  (2022-02-15T19:00:09Z)
• The Limiting Dynamics of SGD: Modified Loss, Phase Space Oscillations, and Anomalous Diffusion [29.489737359897312]
  We study the limiting dynamics of deep neural networks trained with gradient descent (SGD) We show that the key ingredient driving these dynamics is not the original training loss, but rather the combination of a modified loss, which implicitly regularizes the velocity and probability currents, which cause oscillations in phase space.
  arXiv  Detail & Related papers  (2021-07-19T20:18:57Z)
• Just a Momentum: Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problem [12.132641563193584]
  When over loss functions it is common practice to use momentum-based methods rather than vanilla gradient-based loss method. We show how having a mass increases the effective step ball dynamics dynamics leading to up.
  arXiv  Detail & Related papers  (2021-02-23T15:30:57Z)
• Learning non-stationary Langevin dynamics from stochastic observations of latent trajectories [0.0]
  Inferring Langevin equations from data can reveal how transient dynamics of such systems give rise to their function. Here we present a non-stationary framework for inferring the Langevin equation, which explicitly models the observation process and non-stationary latent dynamics. Omitting any of these non-stationary components results in incorrect inference, in which erroneous features arise in the dynamics due to non-stationary data distribution.
  arXiv  Detail & Related papers  (2020-12-29T21:22:21Z)
• Training Generative Adversarial Networks by Solving Ordinary Differential Equations [54.23691425062034]
  We study the continuous-time dynamics induced by GAN training. From this perspective, we hypothesise that instabilities in training GANs arise from the integration error. We experimentally verify that well-known ODE solvers (such as Runge-Kutta) can stabilise training.
  arXiv  Detail & Related papers  (2020-10-28T15:23:49Z)
• Sparse Identification of Nonlinear Dynamical Systems via Reweighted $\ell_1$-regularized Least Squares [62.997667081978825]
  This work proposes an iterative sparse-regularized regression method to recover governing equations of nonlinear systems from noisy state measurements. The aim of this work is to improve the accuracy and robustness of the method in the presence of state measurement noise.
  arXiv  Detail & Related papers  (2020-05-27T08:30:15Z)
• On dissipative symplectic integration with applications to gradient-based optimization [77.34726150561087]
  We propose a geometric framework in which discretizations can be realized systematically. We show that a generalization of symplectic to nonconservative and in particular dissipative Hamiltonian systems is able to preserve rates of convergence up to a controlled error.
  arXiv  Detail & Related papers  (2020-04-15T00:36:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.