Make the Most of Your Data: Changing the Training Data Distribution to Improve In-distribution Generalization Performance
- URL: http://arxiv.org/abs/2404.17768v1
- Date: Sat, 27 Apr 2024 03:30:50 GMT
- Title: Make the Most of Your Data: Changing the Training Data Distribution to Improve In-distribution Generalization Performance
- Authors: Dang Nguyen, Paymon Haddad, Eric Gan, Baharan Mirzasoleiman,
- Abstract summary: We study the inductive bias of gradient descent (GD) with that of sharpness-aware minimization (SAM)
We show that modifying the training data distribution in this way effectively improves the generalization performance on the original data distribution when training with (S)GD.
- Score: 12.472871440252105
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Can we modify the training data distribution to encourage the underlying optimization method toward finding solutions with superior generalization performance on in-distribution data? In this work, we approach this question for the first time by comparing the inductive bias of gradient descent (GD) with that of sharpness-aware minimization (SAM). By studying a two-layer CNN, we prove that SAM learns easy and difficult features more uniformly, particularly in early epochs. That is, SAM is less susceptible to simplicity bias compared to GD. Based on this observation, we propose USEFUL, an algorithm that clusters examples based on the network output early in training and upsamples examples with no easy features to alleviate the pitfalls of the simplicity bias. We show empirically that modifying the training data distribution in this way effectively improves the generalization performance on the original data distribution when training with (S)GD by mimicking the training dynamics of SAM. Notably, we demonstrate that our method can be combined with SAM and existing data augmentation strategies to achieve, to the best of our knowledge, state-of-the-art performance for training ResNet18 on CIFAR10, STL10, CINIC10, Tiny-ImageNet; ResNet34 on CIFAR100; and VGG19 and DenseNet121 on CIFAR10.
Related papers
- Improving Generalization via Meta-Learning on Hard Samples [8.96835934244022]
We show that using hard-to-classify instances in the validation set has both a theoretical connection to, and strong empirical evidence of generalization.
We provide an efficient algorithm for training this meta-optimized model, as well as a simple train-twice for careful comparative study.
arXiv Detail & Related papers (2024-03-18T20:33:44Z) - Take the Bull by the Horns: Hard Sample-Reweighted Continual Training
Improves LLM Generalization [165.98557106089777]
A key challenge is to enhance the capabilities of large language models (LLMs) amid a looming shortage of high-quality training data.
Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets.
We then formalize this strategy into a principled framework of Instance-Reweighted Distributionally Robust Optimization.
arXiv Detail & Related papers (2024-02-22T04:10:57Z) - Simple and effective data augmentation for compositional generalization [64.00420578048855]
We show that data augmentation methods that sample MRs and backtranslate them can be effective for compositional generalization.
Remarkably, sampling from a uniform distribution performs almost as well as sampling from the test distribution.
arXiv Detail & Related papers (2024-01-18T09:13:59Z) - Consistency Regularization for Generalizable Source-free Domain
Adaptation [62.654883736925456]
Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset.
Existing SFDA methods ONLY assess their adapted models on the target training set, neglecting the data from unseen but identically distributed testing sets.
We propose a consistency regularization framework to develop a more generalizable SFDA method.
arXiv Detail & Related papers (2023-08-03T07:45:53Z) - Efficient Augmentation for Imbalanced Deep Learning [8.38844520504124]
We study a convolutional neural network's internal representation of imbalanced image data.
We measure the generalization gap between a model's feature embeddings in the training and test sets, showing that the gap is wider for minority classes.
This insight enables us to design an efficient three-phase CNN training framework for imbalanced data.
arXiv Detail & Related papers (2022-07-13T09:43:17Z) - 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) - To be Critical: Self-Calibrated Weakly Supervised Learning for Salient
Object Detection [95.21700830273221]
Weakly-supervised salient object detection (WSOD) aims to develop saliency models using image-level annotations.
We propose a self-calibrated training strategy by explicitly establishing a mutual calibration loop between pseudo labels and network predictions.
We prove that even a much smaller dataset with well-matched annotations can facilitate models to achieve better performance as well as generalizability.
arXiv Detail & Related papers (2021-09-04T02:45:22Z) - Regularizing Generative Adversarial Networks under Limited Data [88.57330330305535]
This work proposes a regularization approach for training robust GAN models on limited data.
We show a connection between the regularized loss and an f-divergence called LeCam-divergence, which we find is more robust under limited training data.
arXiv Detail & Related papers (2021-04-07T17:59:06Z) - Selective Output Smoothing Regularization: Regularize Neural Networks by
Softening Output Distributions [5.725228891050467]
We propose Selective Output Smoothing Regularization, a novel regularization method for training the Convolutional Neural Networks (CNNs)
Inspired by the diverse effects on training from different samples, Selective Output Smoothing Regularization improves the performance by encouraging the model to produce equal logits on incorrect classes.
This plug-and-play regularization method can be conveniently incorporated into almost any CNN-based project without extra hassle.
arXiv Detail & Related papers (2021-03-29T07:21:06Z) - Passive Batch Injection Training Technique: Boosting Network Performance
by Injecting Mini-Batches from a different Data Distribution [39.8046809855363]
This work presents a novel training technique for deep neural networks that makes use of additional data from a distribution that is different from that of the original input data.
To the best of our knowledge, this is the first work that makes use of different data distribution to aid the training of convolutional neural networks (CNNs)
arXiv Detail & Related papers (2020-06-08T08:17:32Z)
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.