Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok
This paper focuses on predicting the occurrence of grokking in neural networks, a phenomenon in which perfect generalization emerges long after signs of overfitting or memorization are observed. It has been reported that grokking can only be observed with certain hyper-parameters. This makes it critical to identify the parameters that lead to grokking. However, since grokking occurs after a large number of epochs, searching for the hyper-parameters that lead to it is time-consuming. In this paper, we propose a low-cost method to predict grokking without training for a large number of epochs. In essence, by studying the learning curve of the first few epochs, we show that one can predict whether grokking will occur later on. Specifically, if certain oscillations occur in the early epochs, one can expect grokking to occur if the model is trained for a much longer period of time. We propose using the spectral signature of a learning curve derived by applying the Fourier transform to quantify the amplitude of low-frequency components to detect the presence of such oscillations. We also present additional experiments aimed at explaining the cause of these oscillations and characterizing the loss landscape.
Code (0)
등록된 구현이 없습니다.
Tasks
MemorizationSimilar Papers 제목 키워드 기반
Omnigrok: Grokking Beyond Algorithmic Data
Grokking, the unusual phenomenon for algorithmic datasets where generalization happens long after overfitting the training data, has remained elusive. We aim to understand grokking by analyzing the loss landscapes of neu…
AttributeRepresentation LearningThe Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon
The grokking phenomenon as reported by Power et al. ( arXiv:2201.02177 ) refers to a regime where a long period of overfitting is followed by a seemingly sudden transition to perfect generalization. In this paper, we att…
Inductive BiasTowards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials
Grokking has been actively explored to reveal the mystery of delayed generalization and identifying interpretable representations and algorithms inside the grokked models is a suggestive hint to understanding its mechani…
Where to find Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test
Grokking, i.e., test performance keeps improving long after training loss converged, has been recently witnessed in neural network training, making the mechanism of generalization and other emerging capabilities such as …
Code GenerationLarge Language ModelMathMemorizationUnderstanding Grokking Through A Robustness Viewpoint
Recently, an interesting phenomenon called grokking has gained much attention, where generalization occurs long after the models have initially overfitted the training data. We try to understand this seemingly strange ph…