Bridging Lottery ticket and Grokking: Is Weight Norm Sufficient to Explain Delayed Generalization?
- URL: http://arxiv.org/abs/2310.19470v2
- Date: Thu, 9 May 2024 10:21:43 GMT
- Title: Bridging Lottery ticket and Grokking: Is Weight Norm Sufficient to Explain Delayed Generalization?
- Authors: Gouki Minegishi, Yusuke Iwasawa, Yutaka Matsuo,
- Abstract summary: We aim to analyze the mechanism of grokking from the lottery ticket hypothesis.
We refer to theseworks as ''Grokking tickets''
We show that the lottery tickets drastically accelerate grokking compared to the dense networks.
- Score: 27.020990219204343
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Grokking is one of the most surprising puzzles in neural network generalization: a network first reaches a memorization solution with perfect training accuracy and poor generalization, but with further training, it reaches a perfectly generalized solution. We aim to analyze the mechanism of grokking from the lottery ticket hypothesis, identifying the process to find the lottery tickets (good sparse subnetworks) as the key to describing the transitional phase between memorization and generalization. We refer to these subnetworks as ''Grokking tickets'', which is identified via magnitude pruning after perfect generalization. First, using ''Grokking tickets'', we show that the lottery tickets drastically accelerate grokking compared to the dense networks on various configurations (MLP and Transformer, and an arithmetic and image classification tasks). Additionally, to verify that ''Grokking ticket'' are a more critical factor than weight norms, we compared the ''good'' subnetworks with a dense network having the same L1 and L2 norms. Results show that the subnetworks generalize faster than the controlled dense model. In further investigations, we discovered that at an appropriate pruning rate, grokking can be achieved even without weight decay. We also show that speedup does not happen when using tickets identified at the memorization solution or transition between memorization and generalization or when pruning networks at the initialization (Random pruning, Grasp, SNIP, and Synflow). The results indicate that the weight norm of network parameters is not enough to explain the process of grokking, but the importance of finding good subnetworks to describe the transition from memorization to generalization. The implementation code can be accessed via this link: \url{https://github.com/gouki510/Grokking-Tickets}.
Related papers
- 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) - Explaining grokking through circuit efficiency [4.686548060335767]
grokking is a network with perfect training accuracy but poor generalisation will transition to perfect generalisation.
We make and confirm four novel predictions about grokking, providing significant evidence in favour of our explanation.
We demonstrate two novel and surprising behaviours: ungrokking, in which a network regresses from perfect to low test accuracy, and semi-grokking, in which a network shows delayed generalisation to partial rather than perfect test accuracy.
arXiv Detail & Related papers (2023-09-05T17:00:24Z) - Dual Lottery Ticket Hypothesis [71.95937879869334]
Lottery Ticket Hypothesis (LTH) provides a novel view to investigate sparse network training and maintain its capacity.
In this work, we regard the winning ticket from LTH as the subnetwork which is in trainable condition and its performance as our benchmark.
We propose a simple sparse network training strategy, Random Sparse Network Transformation (RST), to substantiate our DLTH.
arXiv Detail & Related papers (2022-03-08T18:06:26Z) - Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets [127.56361320894861]
Lottery ticket hypothesis (LTH) has shown that dense models contain highly sparseworks (i.e., winning tickets) that can be trained in isolation to match full accuracy.
In this paper, we demonstrate the first positive result that a structurally sparse winning ticket can be effectively found in general.
Specifically, we first "re-fill" pruned elements back in some channels deemed to be important, and then "re-group" non-zero elements to create flexible group-wise structural patterns.
arXiv Detail & Related papers (2022-02-09T21:33:51Z) - Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity
on Pruned Neural Networks [79.74580058178594]
We analyze the performance of training a pruned neural network by analyzing the geometric structure of the objective function.
We show that the convex region near a desirable model with guaranteed generalization enlarges as the neural network model is pruned.
arXiv Detail & Related papers (2021-10-12T01:11:07Z) - The Elastic Lottery Ticket Hypothesis [106.79387235014379]
Lottery Ticket Hypothesis raises keen attention to identifying sparse trainableworks or winning tickets.
The most effective method to identify such winning tickets is still Iterative Magnitude-based Pruning.
We propose a variety of strategies to tweak the winning tickets found from different networks of the same model family.
arXiv Detail & Related papers (2021-03-30T17:53:45Z) - Good Students Play Big Lottery Better [84.6111281091602]
Lottery ticket hypothesis suggests that a dense neural network contains a sparse sub-network that can match the test accuracy of the original dense net.
Recent studies demonstrate that a sparse sub-network can still be obtained by using a rewinding technique.
This paper proposes a new, simpler and yet powerful technique for re-training the sub-network, called "Knowledge Distillation ticket" (KD ticket)
arXiv Detail & Related papers (2021-01-08T23:33:53Z) - Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot [55.37967301483917]
Conventional wisdom of pruning algorithms suggests that pruning methods exploit information from training data to find goodworks.
In this paper, we conduct sanity checks for the above beliefs on several recent unstructured pruning methods.
We propose a series of simple emphdata-independent prune ratios for each layer, and randomly prune each layer accordingly to get a subnetwork.
arXiv Detail & Related papers (2020-09-22T17:36:17Z)
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.