Improving Generalization and Convergence by Enhancing Implicit Regularization

• URL: http://arxiv.org/abs/2405.20763v4
• Date: Thu, 31 Oct 2024 11:28:58 GMT
• Title: Improving Generalization and Convergence by Enhancing Implicit Regularization
• Authors: Mingze Wang, Jinbo Wang, Haotian He, Zilin Wang, Guanhua Huang, Feiyu Xiong, Zhiyu Li, Weinan E, Lei Wu,
• Abstract summary: Implicit Regularization Enhancement (IRE) framework to accelerate the discovery of flat solutions in deep learning. IRE decouples the dynamics of flat and sharp directions, which boosts the sharpness reduction along flat directions. We show that IRE can be practically incorporated with em generic bases without introducing significant computational overload.
• Score: 15.806923167905026
• License:
• Abstract: In this work, we propose an Implicit Regularization Enhancement (IRE) framework to accelerate the discovery of flat solutions in deep learning, thereby improving generalization and convergence. Specifically, IRE decouples the dynamics of flat and sharp directions, which boosts the sharpness reduction along flat directions while maintaining the training stability in sharp directions. We show that IRE can be practically incorporated with {\em generic base optimizers} without introducing significant computational overload. Experiments show that IRE consistently improves the generalization performance for image classification tasks across a variety of benchmark datasets (CIFAR-10/100, ImageNet) and models (ResNets and ViTs). Surprisingly, IRE also achieves a $2\times$ {\em speed-up} compared to AdamW in the pre-training of Llama models (of sizes ranging from 60M to 229M) on datasets including Wikitext-103, Minipile, and Openwebtext. Moreover, we provide theoretical guarantees, showing that IRE can substantially accelerate the convergence towards flat minima in Sharpness-aware Minimization (SAM).

Related papers

• Efficient and Versatile Robust Fine-Tuning of Zero-shot Models [34.27380518351181]
  We introduce Robust Adapter (R-Adapter), a novel method for fine-tuning zero-shot models to downstream tasks. Our method integrates lightweight modules into the pre-trained model and employs novel self-ensemble techniques to boost OOD robustness and reduce storage expenses substantially. Our experiments demonstrate that R-Adapter achieves state-of-the-art performance across a diverse set of tasks, tuning only 13% of the parameters of the CLIP encoders.
  arXiv  Detail & Related papers  (2024-08-11T11:37:43Z)
• CR-SAM: Curvature Regularized Sharpness-Aware Minimization [8.248964912483912]
  Sharpness-Aware Minimization (SAM) aims to enhance the generalizability by minimizing worst-case loss using one-step gradient ascent as an approximation. In this paper, we introduce a normalized Hessian trace to accurately measure the curvature of loss landscape on em both training and test sets. In particular, to counter excessive non-linearity of loss landscape, we propose Curvature Regularized SAM (CR-SAM)
  arXiv  Detail & Related papers  (2023-12-21T03:46:29Z)
• Adaptive Data Augmentation for Contrastive Learning [12.526573160980124]
  We propose AdDA, which implements a closed-loop feedback structure to a generic contrastive learning network. AdDA works by allowing the network to adaptively adjust the augmentation compositions according to the real-time feedback.
  arXiv  Detail & Related papers  (2023-04-05T14:19:38Z)
• Unifying Synergies between Self-supervised Learning and Dynamic Computation [53.66628188936682]
  We present a novel perspective on the interplay between SSL and DC paradigms. We show that it is feasible to simultaneously learn a dense and gated sub-network from scratch in a SSL setting. The co-evolution during pre-training of both dense and gated encoder offers a good accuracy-efficiency trade-off.
  arXiv  Detail & Related papers  (2023-01-22T17:12:58Z)
• Sharpness-Aware Training for Free [163.1248341911413]
  SharpnessAware Minimization (SAM) has shown that minimizing a sharpness measure, which reflects the geometry of the loss landscape, can significantly reduce the generalization error. Sharpness-Aware Training Free (SAF) mitigates the sharp landscape at almost zero computational cost over the base. SAF ensures the convergence to a flat minimum with improved capabilities.
  arXiv  Detail & Related papers  (2022-05-27T16:32:43Z)
• Sparsity Winning Twice: Better Robust Generalization from More Efficient Training [94.92954973680914]
  We introduce two alternatives for sparse adversarial training: (i) static sparsity and (ii) dynamic sparsity. We find both methods to yield win-win: substantially shrinking the robust generalization gap and alleviating the robust overfitting. Our approaches can be combined with existing regularizers, establishing new state-of-the-art results in adversarial training.
  arXiv  Detail & Related papers  (2022-02-20T15:52:08Z)
• Efficient Sharpness-aware Minimization for Improved Training of Neural Networks [146.2011175973769]
  This paper proposes Efficient Sharpness Aware Minimizer (M) which boosts SAM s efficiency at no cost to its generalization performance. M includes two novel and efficient training strategies-StochasticWeight Perturbation and Sharpness-Sensitive Data Selection. We show, via extensive experiments on the CIFAR and ImageNet datasets, that ESAM enhances the efficiency over SAM from requiring 100% extra computations to 40% vis-a-vis bases.
  arXiv  Detail & Related papers  (2021-10-07T02:20:37Z)
• When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations [111.44860506703307]
  Vision Transformers (ViTs) and existing VisionNets signal efforts on replacing hand-wired features or inductive throughputs with general-purpose neural architectures. This paper investigates ViTs and Res-Mixers from the lens of loss geometry, intending to improve the models' data efficiency at training and inference. We show that the improved robustness attributes to sparser active neurons in the first few layers. The resultant ViTs outperform Nets of similar size and smoothness when trained from scratch on ImageNet without large-scale pretraining or strong data augmentations.
  arXiv  Detail & Related papers  (2021-06-03T02:08:03Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.