Grokking Explained: A Statistical Phenomenon

• URL: http://arxiv.org/abs/2502.01774v1
• Date: Mon, 03 Feb 2025 19:28:11 GMT
• Title: Grokking Explained: A Statistical Phenomenon
• Authors: Breno W. Carvalho, Artur S. d'Avila Garcez, Luís C. Lamb, Emílio Vital Brazil,
• Abstract summary: 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.
• Score: 4.113597666007784
• License:
• Abstract: 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 challenges conventional understanding of the training dynamics in deep learning networks. In this paper, we formalize and investigate grokking, highlighting that a key factor in its emergence is a distribution shift between training and test data. We introduce two synthetic datasets specifically designed to analyze grokking. One dataset examines the impact of limited sampling, and the other investigates transfer learning's role in grokking. By inducing distribution shifts through controlled imbalanced sampling of sub-categories, we systematically reproduce the phenomenon, demonstrating that while small-sampling is strongly associated with grokking, it is not its cause. Instead, small-sampling serves as a convenient mechanism for achieving the necessary distribution shift. We also show that when classes form an equivariant map, grokking can be explained by the model's ability to learn from similar classes or sub-categories. Unlike earlier work suggesting that grokking primarily arises from high regularization and sparse data, we demonstrate that it can also occur with dense data and minimal hyper-parameter tuning. Our findings deepen the understanding of grokking and pave the way for developing better stopping criteria in future training processes.

Related papers

• Learning from Neighbors: Category Extrapolation for Long-Tail Learning [62.30734737735273]
  We offer a novel perspective on long-tail learning, inspired by an observation: datasets with finer granularity tend to be less affected by data imbalance. We introduce open-set auxiliary classes that are visually similar to existing ones, aiming to enhance representation learning for both head and tail classes. To prevent the overwhelming presence of auxiliary classes from disrupting training, we introduce a neighbor-silencing loss.
  arXiv  Detail & Related papers  (2024-10-21T13:06:21Z)
• Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning [100.7407460674153]
  Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks. To mitigate the problem, a line of methods propose to replay the data of experienced tasks when learning new tasks. However, it is not expected in practice considering the memory constraint or data privacy issue. As a replacement, data-free data replay methods are proposed by inverting samples from the classification model.
  arXiv  Detail & Related papers  (2024-01-12T12:51:12Z)
• Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning? [58.942118128503104]
  Causal confusion is a phenomenon where an agent learns a policy that reflects imperfect spurious correlations in the data. This phenomenon is particularly pronounced in domains such as robotics. In this paper, we study causal confusion in offline reinforcement learning.
  arXiv  Detail & Related papers  (2023-12-28T17:54:56Z)
• Understanding Grokking Through A Robustness Viewpoint [3.23379981095083]
  We show that the popular $l$ norm (metric) of the neural network is actually a sufficient condition for grokking. We propose new metrics based on robustness and information theory and find that our new metrics correlate well with the grokking phenomenon and may be used to predict grokking.
  arXiv  Detail & Related papers  (2023-11-11T15:45:44Z)
• Grokking phase transitions in learning local rules with gradient descent [0.0]
  We show that grokking is a phase transition and find exact analytic expressions for the critical exponents, grokking probability, and grokking time distribution. We numerically analyse the connection between structure formation and grokking.
  arXiv  Detail & Related papers  (2022-10-26T11:07:04Z)
• Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasets [24.551465814633325]
  Deep neural networks usually perform poorly when the training dataset suffers from extreme class imbalance. Recent studies found that directly training with out-of-distribution data in a semi-supervised manner would harm the generalization performance. We propose a novel method called Open-sampling, which utilizes open-set noisy labels to re-balance the class priors of the training dataset.
  arXiv  Detail & Related papers  (2022-06-17T14:29:52Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning [93.38239238988719]
  We propose to enable deep neural networks with the ability to learn the sample relationships from each mini-batch. BatchFormer is applied into the batch dimension of each mini-batch to implicitly explore sample relationships during training. We perform extensive experiments on over ten datasets and the proposed method achieves significant improvements on different data scarcity applications.
  arXiv  Detail & Related papers  (2022-03-03T05:31:33Z)
• Analyzing Overfitting under Class Imbalance in Neural Networks for Image Segmentation [19.259574003403998]
  In image segmentation neural networks may overfit to the foreground samples from small structures. In this study, we provide new insights on the problem of overfitting under class imbalance by inspecting the network behavior.
  arXiv  Detail & Related papers  (2021-02-20T14:57:58Z)
• Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision [57.14468881854616]
  We propose an auxiliary training objective that improves the generalization capabilities of neural networks. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
  arXiv  Detail & Related papers  (2020-04-20T02:47:49Z)
• Imbalanced Data Learning by Minority Class Augmentation using Capsule Adversarial Networks [31.073558420480964]
  We propose a method to restore the balance in imbalanced images, by coalescing two concurrent methods. In our model, generative and discriminative networks play a novel competitive game. The coalescing of capsule-GAN is effective at recognizing highly overlapping classes with much fewer parameters compared with the convolutional-GAN.
  arXiv  Detail & Related papers  (2020-04-05T12:36:06Z)

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.