Why Do We Need Weight Decay in Modern Deep Learning?

• URL: http://arxiv.org/abs/2310.04415v2
• Date: Mon, 04 Nov 2024 23:21:13 GMT
• Title: Why Do We Need Weight Decay in Modern Deep Learning?
• Authors: Francesco D'Angelo, Maksym Andriushchenko, Aditya Varre, Nicolas Flammarion,
• Abstract summary: Weight decay is a technique for training state-of-the-art deep networks from image classification to large language models. In this work, we highlight that the role of weight decay in modern deep learning is different from its regularization effect studied in classical learning theory. For deep networks on vision tasks trained with multipass SGD, we show how weight decay modifies the optimization dynamics enhancing the implicit regularization of SGD.
• Score: 24.81634291051533
• License:
• Abstract: Weight decay is a broadly used technique for training state-of-the-art deep networks from image classification to large language models. Despite its widespread usage and being extensively studied in the classical literature, its role remains poorly understood for deep learning. In this work, we highlight that the role of weight decay in modern deep learning is different from its regularization effect studied in classical learning theory. For deep networks on vision tasks trained with multipass SGD, we show how weight decay modifies the optimization dynamics enhancing the ever-present implicit regularization of SGD via the loss stabilization mechanism. In contrast, for large language models trained with nearly one-epoch training, we describe how weight decay balances the bias-variance tradeoff in stochastic optimization leading to lower training loss and improved training stability. Overall, we present a unifying perspective from ResNets on vision tasks to LLMs: weight decay is never useful as an explicit regularizer but instead changes the training dynamics in a desirable way. The code is available at https://github.com/tml-epfl/why-weight-decay

Related papers

• Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models [27.847140934456288]
  This paper proposes a new weight decay technique, Selective Projection Decay (SPD) SPD selectively imposes a strong penalty on certain layers while allowing others to change freely. When equipped with SPD, Adam consistently provides better in-distribution robustness and out-of-distribution performance on benchmarks.
  arXiv  Detail & Related papers  (2024-11-03T23:36:53Z)
• Normalization and effective learning rates in reinforcement learning [52.59508428613934]
  Normalization layers have recently experienced a renaissance in the deep reinforcement learning and continual learning literature. We show that normalization brings with it a subtle but important side effect: an equivalence between growth in the norm of the network parameters and decay in the effective learning rate. We propose to make the learning rate schedule explicit with a simple re- parameterization which we call Normalize-and-Project.
  arXiv  Detail & Related papers  (2024-07-01T20:58:01Z)
• Improved Generalization of Weight Space Networks via Augmentations [53.87011906358727]
  Learning in deep weight spaces (DWS) is an emerging research direction, with applications to 2D and 3D neural fields (INRs, NeRFs) We empirically analyze the reasons for this overfitting and find that a key reason is the lack of diversity in DWS datasets. To address this, we explore strategies for data augmentation in weight spaces and propose a MixUp method adapted for weight spaces.
  arXiv  Detail & Related papers  (2024-02-06T15:34:44Z)
• HyperSparse Neural Networks: Shifting Exploration to Exploitation through Adaptive Regularization [18.786142528591355]
  Sparse neural networks are a key factor in developing resource-efficient machine learning applications. We propose the novel and powerful sparse learning method Adaptive Regularized Training (ART) to compress dense into sparse networks. Our method compresses the pre-trained model knowledge into the weights of highest magnitude.
  arXiv  Detail & Related papers  (2023-08-14T14:18:11Z)
• Long-Tailed Recognition via Weight Balancing [66.03068252811993]
  Naive training produces models that are biased toward common classes in terms of higher accuracy. We investigate three techniques to balance weights, L2-normalization, weight decay, and MaxNorm. Our approach achieves the state-of-the-art accuracy on five standard benchmarks.
  arXiv  Detail & Related papers  (2022-03-27T03:26:31Z)
• Powerpropagation: A sparsity inducing weight reparameterisation [65.85142037667065]
  We introduce Powerpropagation, a new weight- parameterisation for neural networks that leads to inherently sparse models. Models trained in this manner exhibit similar performance, but have a distribution with markedly higher density at zero, allowing more parameters to be pruned safely. Here, we combine Powerpropagation with a traditional weight-pruning technique as well as recent state-of-the-art sparse-to-sparse algorithms, showing superior performance on the ImageNet benchmark.
  arXiv  Detail & Related papers  (2021-10-01T10:03:57Z)
• FixNorm: Dissecting Weight Decay for Training Deep Neural Networks [7.820667552233989]
  We propose a new training method called FixNorm, which discards weight decay and directly controls the two mechanisms. On ImageNet classification task, training EfficientNet-B0 with FixNorm achieves 77.7%, which outperforms the original baseline by a clear margin.
  arXiv  Detail & Related papers  (2021-03-29T05:41:56Z)
• The Implicit Biases of Stochastic Gradient Descent on Deep Neural Networks with Batch Normalization [44.30960913470372]
  Deep neural networks with batch normalization (BN-DNNs) are invariant to weight rescaling due to their normalization operations. We investigate the implicit biases of gradient descent (SGD) on BN-DNNs to provide a theoretical explanation for the efficacy of weight decay.
  arXiv  Detail & Related papers  (2021-02-06T03:40:20Z)
• On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective [90.39123717733334]
  We present the first practical scheduler for weight decay, called the Scheduled Weight Decay (SWD) method. Our experiments also support that SWD indeed mitigates large gradient norms and often significantly outperforms the conventional constant weight decay strategy for Adaptive Moment Estimation (Adam)
  arXiv  Detail & Related papers  (2020-11-23T00:39:49Z)
• Overfitting in adversarially robust deep learning [86.11788847990783]
  We show that overfitting to the training set does in fact harm robust performance to a very large degree in adversarially robust training. We also show that effects such as the double descent curve do still occur in adversarially trained models, yet fail to explain the observed overfitting.
  arXiv  Detail & Related papers  (2020-02-26T15:40:50Z)

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.