Learning time-scales in two-layers neural networks

• URL: http://arxiv.org/abs/2303.00055v3
• Date: Wed, 17 Apr 2024 18:36:27 GMT
• Title: Learning time-scales in two-layers neural networks
• Authors: Raphaël Berthier, Andrea Montanari, Kangjie Zhou,
• Abstract summary: We study the gradient flow dynamics of a wide two-layer neural network in high-dimension. Based on new rigorous results, we propose a scenario for the learning dynamics in this setting.
• Score: 11.878594839685471
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Gradient-based learning in multi-layer neural networks displays a number of striking features. In particular, the decrease rate of empirical risk is non-monotone even after averaging over large batches. Long plateaus in which one observes barely any progress alternate with intervals of rapid decrease. These successive phases of learning often take place on very different time scales. Finally, models learnt in an early phase are typically `simpler' or `easier to learn' although in a way that is difficult to formalize. Although theoretical explanations of these phenomena have been put forward, each of them captures at best certain specific regimes. In this paper, we study the gradient flow dynamics of a wide two-layer neural network in high-dimension, when data are distributed according to a single-index model (i.e., the target function depends on a one-dimensional projection of the covariates). Based on a mixture of new rigorous results, non-rigorous mathematical derivations, and numerical simulations, we propose a scenario for the learning dynamics in this setting. In particular, the proposed evolution exhibits separation of timescales and intermittency. These behaviors arise naturally because the population gradient flow can be recast as a singularly perturbed dynamical system.

Related papers

• Gradient-free training of recurrent neural networks [3.272216546040443]
  We introduce a computational approach to construct all weights and biases of a recurrent neural network without using gradient-based methods. The approach is based on a combination of random feature networks and Koopman operator theory for dynamical systems. In computational experiments on time series, forecasting for chaotic dynamical systems, and control problems, we observe that the training time and forecasting accuracy of the recurrent neural networks we construct are improved.
  arXiv  Detail & Related papers  (2024-10-30T21:24:34Z)
• Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecasting [50.901984244738806]
  We show how to model the evolutionary and multi-scale interactions of time series. In particular, we first provide a hierarchical graph structure cooperated with the dilated convolution to capture the scale-specific correlations. A unified neural network is provided to integrate the components above to get the final prediction.
  arXiv  Detail & Related papers  (2022-06-28T08:11:12Z)
• Multi-scale Feature Learning Dynamics: Insights for Double Descent [71.91871020059857]
  We study the phenomenon of "double descent" of the generalization error. We find that double descent can be attributed to distinct features being learned at different scales.
  arXiv  Detail & Related papers  (2021-12-06T18:17:08Z)
• Training Integrable Parameterizations of Deep Neural Networks in the Infinite-Width Limit [0.0]
  Large-width dynamics has emerged as a fruitful viewpoint and led to practical insights on real-world deep networks. For two-layer neural networks, it has been understood that the nature of the trained model radically changes depending on the scale of the initial random weights. We propose various methods to avoid this trivial behavior and analyze in detail the resulting dynamics.
  arXiv  Detail & Related papers  (2021-10-29T07:53:35Z)
• Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks [68.8204255655161]
  Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks. We explore the diversity of the neurons within the hidden layer during the learning process. We analyze how the diversity of the neurons affects predictions of the model.
  arXiv  Detail & Related papers  (2021-09-20T15:12:16Z)
• Neural ODE Processes [64.10282200111983]
  We introduce Neural ODE Processes (NDPs), a new class of processes determined by a distribution over Neural ODEs. We show that our model can successfully capture the dynamics of low-dimensional systems from just a few data-points.
  arXiv  Detail & Related papers  (2021-03-23T09:32:06Z)
• Early Stopping in Deep Networks: Double Descent and How to Eliminate it [30.61588337557343]
  We show that epoch-wise double descent arises because different parts of the network are learned at different epochs. We study two standard convolutional networks empirically and show that eliminating epoch-wise double descent through adjusting stepsizes of different layers improves the early stopping performance significantly.
  arXiv  Detail & Related papers  (2020-07-20T13:43:33Z)
• Plateau Phenomenon in Gradient Descent Training of ReLU networks: Explanation, Quantification and Avoidance [0.0]
  In general, neural networks are trained by gradient type optimization methods. The loss function decreases rapidly at the beginning of training but then, after a relatively small number of steps, significantly slow down. The present work aims to identify and quantify the root causes of plateau phenomenon.
  arXiv  Detail & Related papers  (2020-07-14T17:33:26Z)
• Liquid Time-constant Networks [117.57116214802504]
  We introduce a new class of time-continuous recurrent neural network models. Instead of declaring a learning system's dynamics by implicit nonlinearities, we construct networks of linear first-order dynamical systems. These neural networks exhibit stable and bounded behavior, yield superior expressivity within the family of neural ordinary differential equations.
  arXiv  Detail & Related papers  (2020-06-08T09:53:35Z)
• The large learning rate phase of deep learning: the catapult mechanism [50.23041928811575]
  We present a class of neural networks with solvable training dynamics. We find good agreement between our model's predictions and training dynamics in realistic deep learning settings. We believe our results shed light on characteristics of models trained at different learning rates.
  arXiv  Detail & Related papers  (2020-03-04T17:52:48Z)

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.