Control of Overfitting with Physics

• URL: http://arxiv.org/abs/2412.10716v1
• Date: Sat, 14 Dec 2024 07:20:33 GMT
• Title: Control of Overfitting with Physics
• Authors: Sergei V. Kozyrev, Ilya A Lopatin, Alexander N Pechen,
• Abstract summary: Overfitting control in machine learning is explained using analogies from physics and biology. For the generative adversarial network (GAN) model, we establish an analogy between GAN and the predator-prey model in biology.
• Score: 44.99833362998488
• License:
• Abstract: While there are many works on the applications of machine learning, not so many of them are trying to understand the theoretical justifications to explain their efficiency. In this work, overfitting control (or generalization property) in machine learning is explained using analogies from physics and biology. For stochastic gradient Langevin dynamics, we show that the Eyring formula of kinetic theory allows to control overfitting in the algorithmic stability approach - when wide minima of the risk function with low free energy correspond to low overfitting. For the generative adversarial network (GAN) model, we establish an analogy between GAN and the predator-prey model in biology. An application of this analogy allows us to explain the selection of wide likelihood maxima and overfitting reduction for GANs.

Related papers

• Hamiltonian bridge: A physics-driven generative framework for targeted pattern control [0.8192907805418583]
  We present a framework that allows us to control patterns at multiple scales, which we dub the "Hamiltonian bridge" We show how optimal control can be utilized to generate complex patterns via an iterative control protocol over pattern forming pdes which can be casted as Euler flows.
  arXiv  Detail & Related papers  (2024-10-16T15:24:54Z)
• A Neural Network Implementation for Free Energy Principle [3.7937771805690392]
  The free energy principle (FEP) has been widely applied to account for various problems in fields such as cognitive science, neuroscience, social interaction, and hermeneutics. This paper gives a preliminary attempt at bridging FEP and machine learning, via a classical neural network model, the Helmholtz machine. Although the Helmholtz machine is not temporal, it gives an ideal parallel to the vanilla FEP and the hierarchical model of the brain, under which the active inference and predictive coding could be formulated coherently.
  arXiv  Detail & Related papers  (2023-06-11T22:14:21Z)
• Learning Neural Constitutive Laws From Motion Observations for Generalizable PDE Dynamics [97.38308257547186]
  Many NN approaches learn an end-to-end model that implicitly models both the governing PDE and material models. We argue that the governing PDEs are often well-known and should be explicitly enforced rather than learned. We introduce a new framework termed "Neural Constitutive Laws" (NCLaw) which utilizes a network architecture that strictly guarantees standard priors.
  arXiv  Detail & Related papers  (2023-04-27T17:42:24Z)
• Convex Analysis of the Mean Field Langevin Dynamics [49.66486092259375]
  convergence rate analysis of the mean field Langevin dynamics is presented. $p_q$ associated with the dynamics allows us to develop a convergence theory parallel to classical results in convex optimization.
  arXiv  Detail & Related papers  (2022-01-25T17:13:56Z)
• Generative Modeling of Turbulence [0.7646713951724012]
  We present a mathematically well founded approach for the synthetic modeling of turbulent flows using generative adversarial networks (GAN) GAN are efficient in simulating turbulence in technically challenging flow problems on the basis of a moderate amount of training date.
  arXiv  Detail & Related papers  (2021-12-05T11:39:14Z)
• Forced Variational Integrator Networks for Prediction and Control of Mechanical Systems [7.538482310185133]
  We show that forced variational integrator networks (FVIN) architecture allows us to accurately account for energy dissipation and external forcing. This can result in highly-data efficient model-based control and can predict on real non-conservative systems.
  arXiv  Detail & Related papers  (2021-06-05T21:39:09Z)
• GEM: Group Enhanced Model for Learning Dynamical Control Systems [78.56159072162103]
  We build effective dynamical models that are amenable to sample-based learning. We show that learning the dynamics on a Lie algebra vector space is more effective than learning a direct state transition model. This work sheds light on a connection between learning of dynamics and Lie group properties, which opens doors for new research directions.
  arXiv  Detail & Related papers  (2021-04-07T01:08:18Z)
• Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration [130.89746032163106]
  We propose ALOE, a new algorithm for learning conditional and unconditional EBMs for discrete structured data. We show that the energy function and sampler can be trained efficiently via a new variational form of power iteration. We present an energy model guided fuzzer for software testing that achieves comparable performance to well engineered fuzzing engines like libfuzzer.
  arXiv  Detail & Related papers  (2020-11-10T19:31:29Z)
• Training End-to-End Analog Neural Networks with Equilibrium Propagation [64.0476282000118]
  We introduce a principled method to train end-to-end analog neural networks by gradient descent. We show mathematically that a class of analog neural networks (called nonlinear resistive networks) are energy-based models. Our work can guide the development of a new generation of ultra-fast, compact and low-power neural networks supporting on-chip learning.
  arXiv  Detail & Related papers  (2020-06-02T23:38:35Z)
• Explainable Machine Learning Control -- robust control and stability analysis [0.0]
  We show how to use symbolic regression methods to infer the optimal control of a dynamical system. We show that there is a considerable advantage of explainable models over less accessible neural networks.
  arXiv  Detail & Related papers  (2020-01-23T08:09:58Z)

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.