Beyond Progress Measures: Theoretical Insights into the Mechanism of Grokking

• URL: http://arxiv.org/abs/2504.03162v2
• Date: Mon, 14 Apr 2025 08:32:27 GMT
• Title: Beyond Progress Measures: Theoretical Insights into the Mechanism of Grokking
• Authors: Zihan Gu, Ruoyu Chen, Hua Zhang, Yue Hu, Xiaochun Cao,
• Abstract summary: Grokking refers to the abrupt improvement in test accuracy after extended overfitting.<n>In this work, we investigate the grokking mechanism underlying the Transformer in the task of prime number operations.
• Score: 50.465604300990904
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Grokking, referring to the abrupt improvement in test accuracy after extended overfitting, offers valuable insights into the mechanisms of model generalization. Existing researches based on progress measures imply that grokking relies on understanding the optimization dynamics when the loss function is dominated solely by the weight decay term. However, we find that this optimization merely leads to token uniformity, which is not a sufficient condition for grokking. In this work, we investigate the grokking mechanism underlying the Transformer in the task of prime number operations. Based on theoretical analysis and experimental validation, we present the following insights: (i) The weight decay term encourages uniformity across all tokens in the embedding space when it is minimized. (ii) The occurrence of grokking is jointly determined by the uniformity of the embedding space and the distribution of the training dataset. Building on these insights, we provide a unified perspective for understanding various previously proposed progress measures and introduce a novel, concise, and effective progress measure that could trace the changes in test loss more accurately. Finally, to demonstrate the versatility of our theoretical framework, we design a dedicated dataset to validate our theory on ResNet-18, successfully showcasing the occurrence of grokking. The code is released at https://github.com/Qihuai27/Grokking-Insight.

Related papers

• Partial Transportability for Domain Generalization [56.37032680901525]
  Building on the theory of partial identification and transportability, this paper introduces new results for bounding the value of a functional of the target distribution.<n>Our contribution is to provide the first general estimation technique for transportability problems.<n>We propose a gradient-based optimization scheme for making scalable inferences in practice.
  arXiv  Detail & Related papers  (2025-03-30T22:06:37Z)
• Towards Understanding the Optimization Mechanisms in Deep Learning [5.281849820329249]
  In this paper, we adopt a distribution estimation perspective to explore the mechanisms of supervised classification using deep neural networks.<n>For the latter, we provide theoretical insights into mechanisms such as over- and probability randomization.
  arXiv  Detail & Related papers  (2025-03-29T08:46:13Z)
• Grokking Explained: A Statistical Phenomenon [4.113597666007784]
  Grokking, or delayed generalization, is an intriguing learning phenomenon where test set loss decreases sharply only after a model's training set loss has converged. This paper formalizes and investigates grokking, highlighting that a key factor in its emergence is a distribution shift between training and test data.
  arXiv  Detail & Related papers  (2025-02-03T19:28:11Z)
• SINDER: Repairing the Singular Defects of DINOv2 [61.98878352956125]
  Vision Transformer models trained on large-scale datasets often exhibit artifacts in the patch token they extract. We propose a novel fine-tuning smooth regularization that rectifies structural deficiencies using only a small dataset.
  arXiv  Detail & Related papers  (2024-07-23T20:34:23Z)
• On the Generalization Ability of Unsupervised Pretraining [53.06175754026037]
  Recent advances in unsupervised learning have shown that unsupervised pre-training, followed by fine-tuning, can improve model generalization. This paper introduces a novel theoretical framework that illuminates the critical factor influencing the transferability of knowledge acquired during unsupervised pre-training to the subsequent fine-tuning phase. Our results contribute to a better understanding of unsupervised pre-training and fine-tuning paradigm, and can shed light on the design of more effective pre-training algorithms.
  arXiv  Detail & Related papers  (2024-03-11T16:23:42Z)
• On the Dynamics Under the Unhinged Loss and Beyond [104.49565602940699]
  We introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze closed-form dynamics. The unhinged loss allows for considering more practical techniques, such as time-vary learning rates and feature normalization.
  arXiv  Detail & Related papers  (2023-12-13T02:11:07Z)
• Boosted Control Functions: Distribution generalization and invariance in confounded models [10.503777692702952]
  We introduce a strong notion of invariance that allows for distribution generalization even in the presence of nonlinear, non-identifiable structural functions.<n>We propose the ControlTwicing algorithm to estimate the Boosted Control Function (BCF) using flexible machine-learning techniques.
  arXiv  Detail & Related papers  (2023-10-09T15:43:46Z)
• Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL [86.0987896274354]
  We first identify a fundamental pattern, self-excitation, as the primary cause of Q-value estimation divergence in offline RL. We then propose a novel Self-Excite Eigenvalue Measure (SEEM) metric to measure the evolving property of Q-network at training. For the first time, our theory can reliably decide whether the training will diverge at an early stage.
  arXiv  Detail & Related papers  (2023-10-06T17:57:44Z)
• Regularization, early-stopping and dreaming: a Hopfield-like setup to address generalization and overfitting [0.0]
  We look for optimal network parameters by applying a gradient descent over a regularized loss function. Within this framework, the optimal neuron-interaction matrices correspond to Hebbian kernels revised by a reiterated unlearning protocol.
  arXiv  Detail & Related papers  (2023-08-01T15:04:30Z)
• Deep Anti-Regularized Ensembles provide reliable out-of-distribution uncertainty quantification [4.750521042508541]
  Deep ensemble often return overconfident estimates outside the training domain. We show that an ensemble of networks with large weights fitting the training data are likely to meet these two objectives. We derive a theoretical framework for this approach and show that the proposed optimization can be seen as a "water-filling" problem.
  arXiv  Detail & Related papers  (2023-04-08T15:25:12Z)
• Toward Certified Robustness Against Real-World Distribution Shifts [65.66374339500025]
  We train a generative model to learn perturbations from data and define specifications with respect to the output of the learned model. A unique challenge arising from this setting is that existing verifiers cannot tightly approximate sigmoid activations. We propose a general meta-algorithm for handling sigmoid activations which leverages classical notions of counter-example-guided abstraction refinement.
  arXiv  Detail & Related papers  (2022-06-08T04:09:13Z)
• Which Invariance Should We Transfer? A Causal Minimax Learning Approach [18.71316951734806]
  We present a comprehensive minimax analysis from a causal perspective. We propose an efficient algorithm to search for the subset with minimal worst-case risk. The effectiveness and efficiency of our methods are demonstrated on synthetic data and the diagnosis of Alzheimer's disease.
  arXiv  Detail & Related papers  (2021-07-05T09:07:29Z)
• Optimization and Generalization of Regularization-Based Continual Learning: a Loss Approximation Viewpoint [35.5156045701898]
  We provide a novel viewpoint of regularization-based continual learning by formulating it as a second-order Taylor approximation of the loss function of each task. Based on this viewpoint, we study the optimization aspects (i.e., convergence) as well as generalization properties (i.e., finite-sample guarantees) of regularization-based continual learning.
  arXiv  Detail & Related papers  (2020-06-19T06:08:40Z)

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.