Tracing the Path to Grokking: Embeddings, Dropout, and Network Activation

• URL: http://arxiv.org/abs/2507.11645v1
• Date: Tue, 15 Jul 2025 18:30:42 GMT
• Title: Tracing the Path to Grokking: Embeddings, Dropout, and Network Activation
• Authors: Ahmed Salah, David Yevick,
• Abstract summary: Grokking refers to delayed generalization in which the increase in test accuracy of a neural network occurs appreciably after the improvement in training accuracy.<n>This paper introduces several practical metrics including variance under dropout, robustness, embedding similarity, and sparsity measures, that can forecast grokking behavior.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Grokking refers to delayed generalization in which the increase in test accuracy of a neural network occurs appreciably after the improvement in training accuracy This paper introduces several practical metrics including variance under dropout, robustness, embedding similarity, and sparsity measures, that can forecast grokking behavior. Specifically, the resilience of neural networks to noise during inference is estimated from a Dropout Robustness Curve (DRC) obtained from the variation of the accuracy with the dropout rate as the model transitions from memorization to generalization. The variance of the test accuracy under stochastic dropout across training checkpoints further exhibits a local maximum during the grokking. Additionally, the percentage of inactive neurons decreases during generalization, while the embeddings tend to a bimodal distribution independent of initialization that correlates with the observed cosine similarity patterns and dataset symmetries. These metrics additionally provide valuable insight into the origin and behaviour of grokking.

Related papers

• Memorization and Regularization in Generative Diffusion Models [5.128303432235475]
  Diffusion models have emerged as a powerful framework for generative modeling.<n>The analysis highlights the need for regularization to avoid reproducing the analytically tractable minimizer.<n>Experiments are evaluated in the context of memorization, and directions for future development of regularization are highlighted.
  arXiv  Detail & Related papers  (2025-01-27T05:17:06Z)
• Fully Heteroscedastic Count Regression with Deep Double Poisson Networks [4.58556584533865]
  Deep Double Poisson Network (DDPN) is a novel neural discrete count regression model.<n>We show that DDPN exhibits robust regression properties similar to heteroscedastic Gaussian models.<n>Experiments on diverse datasets demonstrate that DDPN outperforms current baselines in accuracy, calibration, and out-of-distribution detection.
  arXiv  Detail & Related papers  (2024-06-13T16:02:03Z)
• Semi-Supervised Deep Sobolev Regression: Estimation and Variable Selection by ReQU Neural Network [3.4623717820849476]
  We propose SDORE, a Semi-supervised Deep Sobolev Regressor, for the nonparametric estimation of the underlying regression function and its gradient.<n>Our study includes a thorough analysis of the convergence rates of SDORE in $L2$-norm, achieving the minimax optimality.
  arXiv  Detail & Related papers  (2024-01-09T13:10:30Z)
• GIT: Detecting Uncertainty, Out-Of-Distribution and Adversarial Samples using Gradients and Invariance Transformations [77.34726150561087]
  We propose a holistic approach for the detection of generalization errors in deep neural networks. GIT combines the usage of gradient information and invariance transformations. Our experiments demonstrate the superior performance of GIT compared to the state-of-the-art on a variety of network architectures.
  arXiv  Detail & Related papers  (2023-07-05T22:04:38Z)
• On double-descent in uncertainty quantification in overparametrized models [24.073221004661427]
  Uncertainty quantification is a central challenge in reliable and trustworthy machine learning. We show a trade-off between classification accuracy and calibration, unveiling a double descent like behavior in the calibration curve of optimally regularized estimators. This is in contrast with the empirical Bayes method, which we show to be well calibrated in our setting despite the higher generalization error and overparametrization.
  arXiv  Detail & Related papers  (2022-10-23T16:01:08Z)
• Fluctuations, Bias, Variance & Ensemble of Learners: Exact Asymptotics for Convex Losses in High-Dimension [25.711297863946193]
  We develop a theory for the study of fluctuations in an ensemble of generalised linear models trained on different, but correlated, features. We provide a complete description of the joint distribution of the empirical risk minimiser for generic convex loss and regularisation in the high-dimensional limit.
  arXiv  Detail & Related papers  (2022-01-31T17:44:58Z)
• On the Double Descent of Random Features Models Trained with SGD [78.0918823643911]
  We study properties of random features (RF) regression in high dimensions optimized by gradient descent (SGD) We derive precise non-asymptotic error bounds of RF regression under both constant and adaptive step-size SGD setting. We observe the double descent phenomenon both theoretically and empirically.
  arXiv  Detail & Related papers  (2021-10-13T17:47:39Z)
• Sampling-free Variational Inference for Neural Networks with Multiplicative Activation Noise [51.080620762639434]
  We propose a more efficient parameterization of the posterior approximation for sampling-free variational inference. Our approach yields competitive results for standard regression problems and scales well to large-scale image classification tasks.
  arXiv  Detail & Related papers  (2021-03-15T16:16:18Z)
• And/or trade-off in artificial neurons: impact on adversarial robustness [91.3755431537592]
  Presence of sufficient number of OR-like neurons in a network can lead to classification brittleness and increased vulnerability to adversarial attacks. We define AND-like neurons and propose measures to increase their proportion in the network. Experimental results on the MNIST dataset suggest that our approach holds promise as a direction for further exploration.
  arXiv  Detail & Related papers  (2021-02-15T08:19:05Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)
• Regularizing Class-wise Predictions via Self-knowledge Distillation [80.76254453115766]
  We propose a new regularization method that penalizes the predictive distribution between similar samples. This results in regularizing the dark knowledge (i.e., the knowledge on wrong predictions) of a single network. Our experimental results on various image classification tasks demonstrate that the simple yet powerful method can significantly improve the generalization ability.
  arXiv  Detail & Related papers  (2020-03-31T06:03:51Z)

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.