Precise gradient descent training dynamics for finite-width multi-layer neural networks

• URL: http://arxiv.org/abs/2505.04898v1
• Date: Thu, 08 May 2025 02:19:39 GMT
• Title: Precise gradient descent training dynamics for finite-width multi-layer neural networks
• Authors: Qiyang Han, Masaaki Imaizumi,
• Abstract summary: We provide the first precise distributional characterization of gradient descent iterates for general multi-layer neural networks.<n>Our non-asymptotic state evolution theory captures Gaussian fluctuations in first-layer weights and concentration in deeper-layer weights.
• Score: 8.057006406834466
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we provide the first precise distributional characterization of gradient descent iterates for general multi-layer neural networks under the canonical single-index regression model, in the `finite-width proportional regime' where the sample size and feature dimension grow proportionally while the network width and depth remain bounded. Our non-asymptotic state evolution theory captures Gaussian fluctuations in first-layer weights and concentration in deeper-layer weights, and remains valid for non-Gaussian features. Our theory differs from existing neural tangent kernel (NTK), mean-field (MF) theories and tensor program (TP) in several key aspects. First, our theory operates in the finite-width regime whereas these existing theories are fundamentally infinite-width. Second, our theory allows weights to evolve from individual initializations beyond the lazy training regime, whereas NTK and MF are either frozen at or only weakly sensitive to initialization, and TP relies on special initialization schemes. Third, our theory characterizes both training and generalization errors for general multi-layer neural networks beyond the uniform convergence regime, whereas existing theories study generalization almost exclusively in two-layer settings. As a statistical application, we show that vanilla gradient descent can be augmented to yield consistent estimates of the generalization error at each iteration, which can be used to guide early stopping and hyperparameter tuning. As a further theoretical implication, we show that despite model misspecification, the model learned by gradient descent retains the structure of a single-index function with an effective signal determined by a linear combination of the true signal and the initialization.

Related papers

• Optimization and Generalization Guarantees for Weight Normalization [19.965963460750206]
  We provide the first theoretical characterizations of both optimization and generalization of deep WeightNorm models.<n>We present experimental results which illustrate how the normalization terms and other quantities of theoretical interest relate to the training of WeightNorm networks.
  arXiv  Detail & Related papers  (2024-09-13T15:55:05Z)
• Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion [83.90492831583997]
  We show that a batch-normalized network can keep the optimal signal propagation properties, but avoid exploding gradients in depth. We use a Multi-Layer Perceptron (MLP) with linear activations and batch-normalization that provably has bounded depth. We also design an activation shaping scheme that empirically achieves the same properties for certain non-linear activations.
  arXiv  Detail & Related papers  (2023-10-03T12:35:02Z)
• Gradient Descent in Neural Networks as Sequential Learning in RKBS [63.011641517977644]
  We construct an exact power-series representation of the neural network in a finite neighborhood of the initial weights. We prove that, regardless of width, the training sequence produced by gradient descent can be exactly replicated by regularized sequential learning.
  arXiv  Detail & Related papers  (2023-02-01T03:18:07Z)
• A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks [49.870593940818715]
  We study the infinite-width limit of a type of three-layer NN model whose first layer is random and fixed. Our theory accommodates different scaling choices of the model, resulting in two regimes of the MF limit that demonstrate distinctive behaviors.
  arXiv  Detail & Related papers  (2022-10-28T17:26:27Z)
• Mean-field Analysis of Piecewise Linear Solutions for Wide ReLU Networks [83.58049517083138]
  We consider a two-layer ReLU network trained via gradient descent. We show that SGD is biased towards a simple solution. We also provide empirical evidence that knots at locations distinct from the data points might occur.
  arXiv  Detail & Related papers  (2021-11-03T15:14:20Z)
• 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)
• The edge of chaos: quantum field theory and deep neural networks [0.0]
  We explicitly construct the quantum field theory corresponding to a general class of deep neural networks. We compute the loop corrections to the correlation function in a perturbative expansion in the ratio of depth $T$ to width $N$. Our analysis provides a first-principles approach to the rapidly emerging NN-QFT correspondence, and opens several interesting avenues to the study of criticality in deep neural networks.
  arXiv  Detail & Related papers  (2021-09-27T18:00:00Z)
• Nonasymptotic theory for two-layer neural networks: Beyond the bias-variance trade-off [10.182922771556742]
  We present a nonasymptotic generalization theory for two-layer neural networks with ReLU activation function. We show that overparametrized random feature models suffer from the curse of dimensionality and thus are suboptimal.
  arXiv  Detail & Related papers  (2021-06-09T03:52:18Z)
• A Neural Network Perturbation Theory Based on the Born Series [0.0]
  Taylor coefficients of deep neural networks (DNNs) still appear mainly in the light of interpretability studies. This gap motivates a general formulation of neural network (NN) Taylor expansions. We show that NNs adapt their derivatives mainly to the leading order of the target function's Taylor expansion.
  arXiv  Detail & Related papers  (2020-09-07T15:54:27Z)
• Revisiting Initialization of Neural Networks [72.24615341588846]
  We propose a rigorous estimation of the global curvature of weights across layers by approximating and controlling the norm of their Hessian matrix. Our experiments on Word2Vec and the MNIST/CIFAR image classification tasks confirm that tracking the Hessian norm is a useful diagnostic tool.
  arXiv  Detail & Related papers  (2020-04-20T18:12:56Z)
• Kernel and Rich Regimes in Overparametrized Models [69.40899443842443]
  We show that gradient descent on overparametrized multilayer networks can induce rich implicit biases that are not RKHS norms. We also demonstrate this transition empirically for more complex matrix factorization models and multilayer non-linear networks.
  arXiv  Detail & Related papers  (2020-02-20T15:43:02Z)

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.