A Theory of Generalization in Deep Learning

• URL: http://arxiv.org/abs/2605.01172v1
• Date: Sat, 02 May 2026 00:21:36 GMT
• Title: A Theory of Generalization in Deep Learning
• Abstract summary: We present a non-asymptotic theory of generalization in deep learning where the empirical neural tangent kernel partitions the output space.<n>Within the signal channel, minibatch SGD ensures that coherent population signal accumulates via fast linear drift, while idiosyncratic memorization is suppressed into a slow, diffusive random walk.<n>This theory naturally explains disparate phenomena in deep learning theory, such as benign overfitting, double descent, implicit bias, and grokking.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a non-asymptotic theory of generalization in deep learning where the empirical neural tangent kernel partitions the output space. In directions corresponding to signal, error dissipates rapidly; in the vast orthogonal dimensions corresponding to noise, the kernel's near-zero eigenvalues trap residual error in a test-invisible reservoir. Within the signal channel, minibatch SGD ensures that coherent population signal accumulates via fast linear drift, while idiosyncratic memorization is suppressed into a slow, diffusive random walk. We prove generalization survives even when the kernel evolves $\mathcal{O}(1)$ in operator norm, the full feature-learning regime. This theory naturally explains disparate phenomena in deep learning theory, such as benign overfitting, double descent, implicit bias, and grokking. Lastly, we derive an exact population-risk objective from a single training run with no validation data, for any architecture, loss, or optimizer, and prove that it measures precisely the noise in the signal channel. This objective reduces in practice to an SNR preconditioner on top of Adam, adding one state vector at no extra cost; it accelerates grokking by $5 \times$, suppresses memorization in PINNs and implicit neural representations, and improves DPO fine-tuning under noisy preferences while staying $3 \times$ closer to the reference policy.

Related papers

• One-Step Early Stopping Strategy using Neural Tangent Kernel Theory and Rademacher Complexity [0.0]
  The early stopping strategy consists in stopping the training process of a neural network (NN) on a set $S$ of input data before training error is minimal.<n>We give here an analytical estimation of the optimal stopping time involving basically the initial training error vector and the eigenvalues of the neural tangent kernel''
  arXiv  Detail & Related papers  (2024-11-27T23:22:28Z)
• Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization [52.16435732772263]
  Second-order optimization has been shown to accelerate the training of deep neural networks in many applications. However, generalization properties of second-order methods are still being debated. We show for the first time that exact Gauss-Newton (GN) updates take on a tractable form in a class of deep architectures.
  arXiv  Detail & Related papers  (2024-11-12T17:58:40Z)
• Benign Overfitting in Deep Neural Networks under Lazy Training [72.28294823115502]
  We show that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification. Our results indicate that interpolating with smoother functions leads to better generalization.
  arXiv  Detail & Related papers  (2023-05-30T19:37:44Z)
• Learning Low Dimensional State Spaces with Overparameterized Recurrent Neural Nets [57.06026574261203]
  We provide theoretical evidence for learning low-dimensional state spaces, which can also model long-term memory. Experiments corroborate our theory, demonstrating extrapolation via learning low-dimensional state spaces with both linear and non-linear RNNs.
  arXiv  Detail & Related papers  (2022-10-25T14:45:15Z)
• Nonparametric Regression with Shallow Overparameterized Neural Networks Trained by GD with Early Stopping [11.24426822697648]
  We show that trained neural networks are smooth with respect to their inputs when trained by Gradient Descent (GD) In the noise-free case the proof does not rely on any kernelization and can be regarded as a finite-width result.
  arXiv  Detail & Related papers  (2021-07-12T11:56:53Z)
• Towards an Understanding of Benign Overfitting in Neural Networks [104.2956323934544]
  Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss. We examine how these benign overfitting phenomena occur in a two-layer neural network setting. We show that it is possible for the two-layer ReLU network interpolator to achieve a near minimax-optimal learning rate.
  arXiv  Detail & Related papers  (2021-06-06T19:08:53Z)
• RATT: Leveraging Unlabeled Data to Guarantee Generalization [96.08979093738024]
  We introduce a method that leverages unlabeled data to produce generalization bounds. We prove that our bound is valid for 0-1 empirical risk minimization. This work provides practitioners with an option for certifying the generalization of deep nets even when unseen labeled data is unavailable.
  arXiv  Detail & Related papers  (2021-05-01T17:05:29Z)
• Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate [105.62979485062756]
  This paper attempts to characterize the particular regularization effect of SGD in the moderate learning rate regime. We show that SGD converges along the large eigenvalue directions of the data matrix, while GD goes after the small eigenvalue directions.
  arXiv  Detail & Related papers  (2020-11-04T21:07:52Z)
• Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network [20.132432350255087]
  Overparametrized neural networks trained by tangent descent (GD) can provably overfit any training data. This paper studies how well overparametrized neural networks can recover the true target function in the presence of random noises.
  arXiv  Detail & Related papers  (2020-07-06T01:02:23Z)
• When Does Preconditioning Help or Hurt Generalization? [74.25170084614098]
  We show how the textitimplicit bias of first and second order methods affects the comparison of generalization properties. We discuss several approaches to manage the bias-variance tradeoff, and the potential benefit of interpolating between GD and NGD.
  arXiv  Detail & Related papers  (2020-06-18T17:57:26Z)

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.